© 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. 9-RES-JB
    11. 1362
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to identifying, reviewing, monitoring, investigating, evaluating, assessing, and refining various processes and systems

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to identification and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     :(
    -0.66
     rocked
    -0.64
     anyway
    -0.64
     luckily
    -0.63
     anyways
    -0.61
     nodd
    -0.56
    ammy
    -0.55
    ]}
    -0.55
     aback
    -0.55
     sans
    -0.54
    POSITIVE LOGITS
    ibly
    0.84
    ively
    0.78
     and
    0.77
    ingly
    0.75
    itatively
    0.70
     vulnerabilities
    0.69
    iencies
    0.67
     grievances
    0.67
    icipated
    0.65
     &
    0.64
    Activations Density 0.608%

    No Known Activations