© 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. 11-RES-JB
    11. 23853
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progressing with a task or moving forward

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.67
    ynthesis
    -0.63
    regor
    -0.63
    urrection
    -0.62
    ¶ħ
    -0.62
    resp
    -0.62
    initions
    -0.61
    ilation
    -0.61
    ynt
    -0.60
    rors
    -0.60
    POSITIVE LOGITS
     board
    1.16
     track
    1.11
    board
    0.91
    side
    0.88
    track
    0.88
    shore
    0.88
     topic
    0.86
     schedule
    0.85
     top
    0.85
     rails
    0.84
    Activations Density 0.075%

    No Known Activations