© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 12989
    Prev
    Next
    INDEX
    Explanations

    addresses and numeric information within news articles

    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
    230
    +0.13
    0.6%
    218
    +0.10
    0.5%
    98
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.13
    0.10
    310
    +0.10
    0.10
    260
    +0.10
    0.10
    Negative Logits
    nam
    -0.78
    shows
    -0.71
    alyses
    -0.67
    agan
    -0.67
    iqu
    -0.67
    ifice
    -0.67
    ifacts
    -0.67
    etermined
    -0.64
    agall
    -0.62
    iferation
    -0.62
    POSITIVE LOGITS
    mAh
    1.04
    MHz
    0.90
     MHz
    0.89
    bps
    0.86
     miles
    0.85
    çĶ°
    0.85
    rpm
    0.84
     rpm
    0.83
    HQ
    0.82
     ILCS
    0.81
    Activations Density 4.128%

    No Known Activations