© 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. 8-RES-JB
    11. 4544
    Prev
    Next
    INDEX
    Explanations

    unrelated characters and random data rather than specific patterns or themes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensibly
    -0.74
    ction
    -0.72
    tones
    -0.63
    nsic
    -0.60
    eworks
    -0.60
    minist
    -0.56
    isks
    -0.56
    marked
    -0.56
     intending
    -0.56
    ocious
    -0.55
    POSITIVE LOGITS
    ↵
    0.73
     etc
    0.73
    Jr
    0.71
     Norn
    0.67
    ????????
    0.66
    ³³³
    0.66
     constitu
    0.63
    âĵĺ
    0.63
    ################################
    0.62
    Lago
    0.62
    Activations Density 0.137%

    No Known Activations