© 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. 1-RES-JB
    11. 7995
    Prev
    Next
    INDEX
    Explanations

    animals often associated with farming and agriculture, such as chickens, cows, goats, and ducks

    oai_token-act-pair · gpt-3.5-turbo

    references to farm animals and their treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.77
    BN
    -0.75
    BU
    -0.69
     oral
    -0.68
    AMI
    -0.67
    Recommend
    -0.66
    âĸ¬
    -0.65
     insider
    -0.65
     nerve
    -0.64
    UGC
    -0.63
    POSITIVE LOGITS
    hops
    0.99
    paces
    0.97
    pace
    0.85
    ervative
    0.85
    actly
    0.83
    urable
    0.82
    folk
    0.82
    ynthesis
    0.82
    ourced
    0.82
    ourcing
    0.80
    Activations Density 0.015%

    No Known Activations