© 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. 9503
    Prev
    Next
    INDEX
    Explanations

    phrases related to ownership, jurisdiction, and authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to collective rights and responsibilities

    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
    iatus
    -0.76
    iband
    -0.67
     Quarterly
    -0.67
    geoning
    -0.63
     âĨij
    -0.63
    CENT
    -0.62
    ctor
    -0.61
    cium
    -0.60
     DRAG
    -0.59
     Unsure
    -0.59
    POSITIVE LOGITS
     theirs
    1.73
     hers
    1.69
     ours
    1.60
     yours
    1.51
     mine
    1.35
    their
    0.96
     Mine
    0.94
    your
    0.90
    our
    0.86
    his
    0.83
    Activations Density 0.377%

    No Known Activations