© 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. 3-RES-JB
    11. 18907
    Prev
    Next
    INDEX
    Explanations

    phrases indicating impossibility or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impossibility or certainty regarding a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.88
    encer
    -0.88
    anmar
    -0.77
    usters
    -0.76
    encers
    -0.73
    uster
    -0.72
    erville
    -0.71
    uctor
    -0.68
    rum
    -0.65
    rake
    -0.64
    POSITIVE LOGITS
    fare
    0.95
    point
    0.92
    forward
    0.85
    finding
    0.84
    points
    0.80
    aterasu
    0.76
     DAM
    0.73
    ward
    0.70
    sey
    0.70
    pointers
    0.69
    Activations Density 0.053%

    No Known Activations