© 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. 0-RES-JB
    11. 7899
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Daniels."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fri
    -0.72
    late
    -0.65
     det
    -0.65
    touch
    -0.64
     webcam
    -0.64
     snail
    -0.63
    web
    -0.63
     Pokémon
    -0.63
     MT
    -0.62
     PT
    -0.62
    POSITIVE LOGITS
     Daniels
    4.33
     Byrd
    1.29
     Abrams
    1.25
     Davies
    1.13
     Evans
    1.11
     Farrell
    1.10
    Adams
    1.09
     Adams
    1.07
     Davidson
    1.07
     Nichols
    1.06
    Activations Density 0.021%

    No Known Activations