© 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. 8733
    Prev
    Next
    INDEX
    Explanations

    terms related to processes, stages, and conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to processes, patterns, or cultural phenomena

    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
    tics
    -0.80
     finances
    -0.76
    sites
    -0.71
    ockets
    -0.68
    eworks
    -0.66
    poons
    -0.65
    iries
    -0.65
    itters
    -0.64
     sights
    -0.64
    ernels
    -0.64
    POSITIVE LOGITS
     similar
    0.88
     whereby
    0.87
     akin
    0.83
    atical
    0.81
     reminiscent
    0.81
    less
    0.78
     analogous
    0.76
     resembling
    0.71
    like
    0.70
     gradient
    0.69
    Activations Density 0.305%

    No Known Activations