© 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. 6-RES-JB
    11. 21776
    Prev
    Next
    INDEX
    Explanations

    adjectives that express some form of surprise or interest

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that denote unusual or noteworthy qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateurs
    -0.93
    hops
    -0.88
    asters
    -0.82
    hers
    -0.80
    agents
    -0.75
    hots
    -0.75
    assies
    -0.74
    ittees
    -0.72
     depended
    -0.70
    agree
    -0.70
    POSITIVE LOGITS
     combination
    1.03
     tale
    0.99
     situation
    0.95
     piece
    0.92
     twist
    0.91
     array
    0.91
     assortment
    0.90
     scenario
    0.89
     conco
    0.88
     comeback
    0.87
    Activations Density 0.242%

    No Known Activations