© 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. 12200
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a call to action, often related to requesting support or donations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "for" indicating explanations or justifications

    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
    urat
    -0.80
    ILY
    -0.77
    soever
    -0.76
    chenko
    -0.75
    iless
    -0.72
    ettel
    -0.72
    yles
    -0.71
    chnology
    -0.70
    jandro
    -0.70
    acy
    -0.69
    POSITIVE LOGITS
     starters
    1.36
    give
    1.23
     simplicity
    1.09
     reference
    1.08
    got
    1.05
     comparison
    1.05
     sake
    1.04
     clarification
    1.02
    gettable
    0.99
    getting
    0.99
    Activations Density 0.099%

    No Known Activations