© 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. 2-RES-JB
    11. 1402
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically focusing on the name "Rudd" and "Ridley."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rudd."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ________________________
    -0.80
    plates
    -0.77
    ________________________________
    -0.71
    bidden
    -0.68
     corpus
    -0.66
     Renaissance
    -0.66
    gran
    -0.64
    ×ij
    -0.63
    ________________________________________________________________
    -0.63
    meric
    -0.63
    POSITIVE LOGITS
     Rudd
    1.14
    ock
    0.91
    erer
    0.88
    cliffe
    0.86
    olph
    0.86
    uling
    0.86
    aby
    0.85
    omon
    0.85
    enthal
    0.85
    ieri
    0.84
    Activations Density 0.006%

    No Known Activations