© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 3849
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about electronic devices, especially smartphones and computers

    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
    0
    +0.02
    0.5%
    159
    +0.02
    0.4%
    341
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.02
    0.28
    294
    +0.02
    0.04
    255
    +0.01
    0.12
    Negative Logits
    rieg
    -0.14
    esville
    -0.13
    venture
    -0.13
    fred
    -0.13
    nell
    -0.13
    wy
    -0.12
    tein
    -0.12
    swick
    -0.12
    ritch
    -0.12
    creation
    -0.12
    POSITIVE LOGITS
    yah
    0.14
    士
    0.14
    æĸ¹
    0.13
     BaseType
    0.13
    edIn
    0.13
    ya
    0.13
    uri
    0.12
    omi
    0.12
    onent
    0.12
    ents
    0.12
    Activations Density 20.121%

    No Known Activations