© 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. 9038
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases praising or commenting on various things

    oai_token-act-pair · gpt-3.5-turbo

    structured presentation elements and markers in a document

    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
    natureconservancy
    -0.76
    FORMATION
    -0.74
    jong
    -0.71
    ocused
    -0.69
    NetMessage
    -0.67
    "},"
    -0.67
    ivery
    -0.66
    rowth
    -0.66
    ablishment
    -0.66
    ucha
    -0.65
    POSITIVE LOGITS
     caveat
    1.11
     disclaimer
    0.97
     caveats
    0.90
     note
    0.89
    !:
    0.85
     aside
    0.83
     NOTE
    0.81
    *:
    0.74
    :
    0.74
     bonus
    0.73
    Activations Density 0.311%

    No Known Activations