© 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. 4-RES-JB
    11. 2898
    Prev
    Next
    INDEX
    Explanations

    phrases related to aftermath or consequences of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the wake of."

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

    No Comments

    Negative Logits
    afort
    -0.78
    entric
    -0.70
    atem
    -0.63
     Conversation
    -0.63
    allo
    -0.62
     Grape
    -0.62
    inates
    -0.61
    uca
    -0.61
    cision
    -0.61
     mustard
    -0.58
    POSITIVE LOGITS
    achine
    0.95
    fulness
    0.92
     wake
    0.89
    giving
    0.80
    wake
    0.80
    mares
    0.79
    math
    0.78
    ãĤ·ãĥ£
    0.77
    bringer
    0.76
    word
    0.71
    Activations Density 0.008%

    No Known Activations