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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34155
    Prev
    Next
    INDEX
    Explanations

    information and details related to the rear aspect of cars and photography, such as rear features, rear cameras, and rear lighting

    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
    +0.13
    0.5%
    596
    +0.13
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.13
    0.07
    588
    +0.13
    0.08
    356
    +0.12
    0.01
    Negative Logits
    ittee
    -0.91
    âĸĪâĸĪ
    -0.88
    esson
    -0.87
    anwhile
    -0.86
    ensable
    -0.86
    etus
    -0.85
    Ö¼
    -0.83
    etti
    -0.83
    oleon
    -0.80
    achu
    -0.80
    POSITIVE LOGITS
    ward
    1.37
    wards
    1.08
    most
    1.04
    side
    1.03
     axle
    1.02
    bone
    0.95
     tyre
    0.94
     lobe
    0.92
     derail
    0.91
    fed
    0.88
    Activations Density 6.533%

    No Known Activations