© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1841
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'perform' is used

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "perform" in various contexts

    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
    ship
    -0.71
    raft
    -0.70
    brow
    -0.67
    spr
    -0.66
    govtrack
    -0.66
    issue
    -0.65
    rack
    -0.63
    empty
    -0.62
    nesty
    -0.61
    inki
    -0.61
    POSITIVE LOGITS
     abortions
    0.87
     miracles
    0.87
     evaluations
    0.87
     poorly
    0.82
     CPR
    0.80
     duties
    0.79
     stunts
    0.78
    uate
    0.75
     renovations
    0.75
     exceptionally
    0.74
    Activations Density 0.035%

    No Known Activations