Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45276
    Prev
    Next
    INDEX
    Explanations

    references to the website IGN or gaming-related content

    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
    651
    +0.12
    0.6%
    326
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.19
    613
    +0.11
    0.08
    162
    +0.10
    0.06
    Negative Logits
    zynski
    -0.72
    xual
    -0.72
    foot
    -0.71
     Georgian
    -0.71
    tons
    -0.71
     Finnish
    -0.69
     Azerbai
    -0.67
    annis
    -0.67
     Eston
    -0.64
     Fenrir
    -0.64
    POSITIVE LOGITS
    VERTISEMENT
    1.02
    ORED
    0.94
    ution
    0.94
    ITION
    0.91
    ibly
    0.91
    uable
    0.83
     IGN
    0.82
    UTION
    0.81
    ORE
    0.81
    ITE
    0.79
    Activations Density 6.182%

    No Known Activations