© 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. 10057
    Prev
    Next
    INDEX
    Explanations

    short phrases indicating reasons or justifications

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and punctuation that indicate complex or conditional thoughts

    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
    ongo
    -0.67
    ophon
    -0.65
    ann
    -0.63
    yon
    -0.62
    OND
    -0.62
    ortium
    -0.61
    iphate
    -0.59
    ocl
    -0.58
     Forward
    -0.58
    atform
    -0.58
    POSITIVE LOGITS
     etc
    0.90
     lest
    0.87
     respectively
    0.77
     thereby
    0.73
     regardless
    0.72
    but
    0.71
    }"
    0.71
    etc
    0.70
     namely
    0.70
     whereas
    0.70
    Activations Density 0.419%

    No Known Activations