© 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. 10-RES-JB
    11. 9921
    Prev
    Next
    INDEX
    Explanations

    specifications or details within a text

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and punctuation that indicate a change in thought or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waged
    -0.63
    untarily
    -0.60
     toll
    -0.58
     neighb
    -0.58
     designated
    -0.58
    elve
    -0.57
    ogram
    -0.56
    angering
    -0.56
    ixty
    -0.56
     surrendered
    -0.56
    POSITIVE LOGITS
    Quote
    1.08
    Firstly
    1.05
    Anyway
    0.96
    Basically
    0.95
    yeah
    0.93
     Firstly
    0.91
    why
    0.90
    EDIT
    0.88
     Basically
    0.87
     yeah
    0.85
    Activations Density 0.726%

    No Known Activations