© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39829
    Prev
    Next
    INDEX
    Explanations

    statistical information and data related to various topics like demographics, opinions, and economic indicators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    0.9%
    153
    +0.10
    0.5%
    2
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.28
    575
    +0.10
    0.18
    67
    +0.09
    0.15
    Negative Logits
    odox
    -0.76
    RAW
    -0.73
     impunity
    -0.65
     Skinner
    -0.65
    pedia
    -0.64
    èª
    -0.64
    unity
    -0.62
    asso
    -0.62
    ãĤ´ãĥ³
    -0.61
     Cosponsors
    -0.61
    POSITIVE LOGITS
     polled
    0.98
     surveyed
    0.97
     âĶľ
    0.89
     (£
    0.76
     nationwide
    0.75
    total
    0.75
     nationally
    0.74
     total
    0.72
     (~
    0.71
     households
    0.71
    Activations Density 15.252%

    No Known Activations