© 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. 3-RES-JB
    11. 15098
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, political movements, and influential figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "great" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.90
    chedel
    -0.73
     Leilan
    -0.73
    eters
    -0.70
    clips
    -0.69
    utical
    -0.68
    ©¶æ
    -0.68
    meta
    -0.66
    ilus
    -0.66
    ratom
    -0.65
    POSITIVE LOGITS
    sword
    1.03
     strides
    0.95
    itud
    0.84
     apes
    0.76
    reek
    0.76
     pains
    0.75
     Dane
    0.74
     proportions
    0.74
     misfortune
    0.73
    axe
    0.71
    Activations Density 0.036%

    No Known Activations