© 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. 17830
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a generalization or summary

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating general characteristics or descriptions of situations

    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
    antha
    -0.78
    zag
    -0.66
    anth
    -0.65
    glas
    -0.65
    agra
    -0.65
    ham
    -0.64
    gang
    -0.62
    omas
    -0.61
    deep
    -0.61
    İĭ
    -0.61
    POSITIVE LOGITS
     consists
    0.72
     unchanged
    0.70
     (~
    0.69
     consisted
    0.66
     nowadays
    0.66
     (>
    0.65
     unnoticed
    0.64
     revolves
    0.63
     consist
    0.63
     intact
    0.62
    Activations Density 0.038%

    No Known Activations