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. 45331
    Prev
    Next
    INDEX
    Explanations

    information related to educational programs, events, and specific activities within a community

    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
    336
    +0.03
    0.5%
    193
    +0.03
    0.5%
    553
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.03
    0.09
    91
    +0.03
    0.12
    757
    +0.02
    0.07
    Negative Logits
    mens
    -0.18
    productive
    -0.17
    cible
    -0.17
    BG
    -0.17
    Bo
    -0.16
    necessary
    -0.16
    except
    -0.15
    Internal
    -0.15
    ãĥĥ
    -0.15
    Wh
    -0.14
    POSITIVE LOGITS
    idon
    0.17
    axy
    0.17
     dies
    0.17
     wakes
    0.17
     wonders
    0.16
    agraph
    0.15
    avia
    0.15
     retrie
    0.15
     survives
    0.15
     arrives
    0.15
    Activations Density 7.273%

    No Known Activations