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. 45725
    Prev
    Next
    INDEX
    Explanations

    phrases related to symptoms and remedies for hangovers

    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
    526
    +0.14
    0.7%
    288
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.23
    326
    +0.10
    0.22
    444
    +0.10
    0.09
    Negative Logits
    é¾
    -0.77
    ogn
    -0.75
    Reviewer
    -0.74
    anyon
    -0.70
    WI
    -0.66
    cedented
    -0.65
    redibly
    -0.64
    Bone
    -0.62
    zynski
    -0.61
    Downloadha
    -0.61
    POSITIVE LOGITS
    kind
    0.61
    lord
    0.61
    ese
    0.60
    moon
    0.58
    eering
    0.57
     Surprise
    0.56
    agus
    0.55
     cure
    0.55
    edia
    0.55
    bugs
    0.55
    Activations Density 7.976%

    No Known Activations