© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1672
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate a requirement or necessity for action

    oai_token-act-pair · gpt-3.5-turbo

    actions related to searching or making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescence
    -0.72
    oulos
    -0.69
    luaj
    -0.68
    alde
    -0.64
    AAA
    -0.63
    nes
    -0.63
    FM
    -0.62
    ankind
    -0.61
    Merit
    -0.61
    Rust
    -0.59
    POSITIVE LOGITS
     somewhere
    0.94
     manually
    0.93
     oneself
    0.87
    dress
    0.82
     urgently
    0.78
     lest
    0.77
    uper
    0.76
     something
    0.74
     sacrific
    0.72
     compromises
    0.71
    Activations Density 0.293%

    No Known Activations