© 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. 17440
    Prev
    Next
    INDEX
    Explanations

    requests for information or feedback

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or requests for information and contributions from the audience

    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
     srfAttach
    -0.83
     contrace
    -0.70
     clenched
    -0.66
    displayText
    -0.64
     accuser
    -0.63
     CONTROL
    -0.62
    ulic
    -0.61
     Consent
    -0.60
    EStreamFrame
    -0.60
     sovere
    -0.60
    POSITIVE LOGITS
     typo
    0.93
     missed
    0.88
     bugs
    0.87
     additions
    0.87
     inacc
    0.86
     helpful
    0.86
     Helpful
    0.84
    improve
    0.83
     yours
    0.81
     interesting
    0.78
    Activations Density 0.423%

    No Known Activations