© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    verbs related to making a judgment or assessment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of evaluation or judgment

    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
    NetMessage
    -0.77
    eled
    -0.73
    instein
    -0.71
    prus
    -0.71
    por
    -0.68
     recess
    -0.66
    olester
    -0.66
    hemy
    -0.65
    nce
    -0.63
    Es
    -0.63
    POSITIVE LOGITS
     reckoned
    1.29
     reckon
    1.06
    enance
    1.05
    tackle
    0.73
     Doodle
    0.72
     Tac
    0.70
    apter
    0.69
     mast
    0.66
    adays
    0.66
    abouts
    0.64
    Activations Density 0.016%

    No Known Activations