© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3069
    Prev
    Next
    INDEX
    Explanations

    numerical values followed by measurements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approximately" and its variations, indicating approximations or estimations of quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ny
    -0.89
    lined
    -0.76
    enders
    -0.73
    woods
    -0.72
    eyes
    -0.71
    heartedly
    -0.70
    aways
    -0.70
    lining
    -0.69
    sheets
    -0.69
    door
    -0.69
    POSITIVE LOGITS
    ments
    0.85
    dinand
    0.83
    ment
    0.69
     Artemis
    0.68
    atility
    0.67
    tainment
    0.64
    WER
    0.63
    atform
    0.61
     Lafayette
    0.60
    isitions
    0.59
    Activations Density 0.117%

    No Known Activations