© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    actions or outcomes that have a significant impact or consequences

    oai_token-act-pair · gpt-3.5-turbo

    action words that indicate declarations or statements of fact

    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
    sw
    -0.70
    away
    -0.69
    aneous
    -0.68
    nex
    -0.64
    pton
    -0.61
    squ
    -0.59
    tex
    -0.59
    xxx
    -0.59
    yon
    -0.59
    isp
    -0.59
    POSITIVE LOGITS
    ometimes
    1.05
    ilver
    0.94
    ensibly
    0.82
    hift
    0.81
    omething
    0.79
    hirt
    0.77
    everal
    0.72
    olate
    0.71
    rals
    0.69
    uggest
    0.68
    Activations Density 0.467%

    No Known Activations