© 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. 14050
    Prev
    Next
    INDEX
    Explanations

    references to binary code and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to binary files and executable formats

    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
    rir
    -1.04
    neau
    -0.92
    mans
    -0.89
    idan
    -0.84
    uay
    -0.83
    chester
    -0.83
    ndra
    -0.82
    mens
    -0.79
    kers
    -0.79
    bach
    -0.79
    POSITIVE LOGITS
     blob
    1.05
     representation
    0.79
     coded
    0.76
     encoded
    0.76
     decomp
    0.76
     filename
    0.75
     encoding
    0.74
     representations
    0.74
     binaries
    0.74
     binary
    0.73
    Activations Density 0.093%

    No Known Activations