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. 45311
    Prev
    Next
    INDEX
    Explanations

    links for additional information or 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
    447
    +0.18
    0.8%
    311
    +0.14
    0.6%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.18
    0.07
    551
    +0.14
    0.07
    377
    +0.10
    0.13
    Negative Logits
    visors
    -0.75
    itialized
    -0.66
    usterity
    -0.65
    ãĥı
    -0.63
    omore
    -0.63
    amines
    -0.59
    ONSORED
    -0.58
    amac
    -0.58
    iour
    -0.58
     diarrhea
    -0.58
    POSITIVE LOGITS
    tics
    1.21
    abouts
    1.17
    tical
    1.17
    tic
    1.01
    ridges
    0.75
    with
    0.70
    edin
    0.69
     âĢº
    0.69
     guiActiveUn
    0.68
    ford
    0.67
    Activations Density 6.520%

    No Known Activations