© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    common noun phrases relating to characteristics or details of objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finance and production metrics

    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
    hops
    -0.82
    sites
    -0.74
    urrencies
    -0.72
    arenthood
    -0.70
    profits
    -0.69
    events
    -0.69
     establishments
    -0.69
    projects
    -0.68
     Occupations
    -0.67
    units
    -0.67
    POSITIVE LOGITS
     version
    0.84
     variant
    0.78
     vibe
    0.73
     attitude
    0.73
     rating
    0.72
     timetable
    0.72
     designation
    0.71
     identifier
    0.70
     certificate
    0.70
     endorsement
    0.70
    Activations Density 0.761%

    No Known Activations