© 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. 7-RES-JB
    11. 17121
    Prev
    Next
    INDEX
    Explanations

    programming code snippets containing method declarations

    oai_token-act-pair · gpt-3.5-turbo

    code-related constructs and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.98
    Sov
    -0.83
    ebook
    -0.79
    yss
    -0.76
     Chap
    -0.74
    Anth
    -0.74
    д
    -0.74
    apons
    -0.72
    dq
    -0.72
    icism
    -0.70
    POSITIVE LOGITS
     /**
    0.86
     bool
    0.84
     const
    0.83
     override
    0.80
     struct
    0.79
     boolean
    0.78
    void
    0.75
     /*
    0.74
    (){
    0.71
     func
    0.71
    Activations Density 0.146%

    No Known Activations