© 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. 371
    Prev
    Next
    INDEX
    Explanations

    specific references to a person or a group named "Revival"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Rev" and its variations, likely related to reviews or revisions

    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
    ADRA
    -0.78
    holders
    -0.77
    OTH
    -0.70
     Catalonia
    -0.70
     Catalan
    -0.67
     Finnish
    -0.64
     FIGHT
    -0.63
    mates
    -0.62
     Poles
    -0.62
     TOTAL
    -0.62
    POSITIVE LOGITS
    isions
    1.24
    ision
    1.12
    olver
    1.02
    olutions
    1.00
    olves
    0.98
    issions
    0.98
    ising
    0.96
    ivals
    0.96
    idence
    0.93
    ulsion
    0.93
    Activations Density 0.013%

    No Known Activations