© 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. 39815
    Prev
    Next
    INDEX
    Explanations

    links to a specific website

    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
    471
    +0.15
    0.6%
    232
    +0.12
    0.5%
    103
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.15
    0.08
    103
    +0.12
    0.08
    503
    +0.12
    0.04
    Negative Logits
    ivities
    -1.02
    ivity
    -0.86
     nomine
    -0.82
    FTWARE
    -0.77
     butterflies
    -0.72
    Magikarp
    -0.72
     antioxid
    -0.72
    folk
    -0.72
     Balt
    -0.71
    creen
    -0.71
    POSITIVE LOGITS
    ruary
    1.82
    oard
    1.34
    rahim
    1.22
    edia
    1.13
    bies
    1.12
    ulous
    1.12
    uilt
    1.10
    rief
    1.08
    acteria
    1.07
    uild
    1.06
    Activations Density 8.992%

    No Known Activations