© 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. 6-RES-JB
    11. 18468
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures' last names

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossier
    -0.78
    displayText
    -0.77
     myster
    -0.76
     endorsements
    -0.72
     endors
    -0.68
    accompan
    -0.66
     proble
    -0.65
    vana
    -0.64
    ilater
    -0.64
     assistants
    -0.64
    POSITIVE LOGITS
    bre
    0.82
    cone
    0.72
    rame
    0.70
    fruit
    0.69
    Nar
    0.68
    hend
    0.66
    hurst
    0.65
    pload
    0.65
    hoff
    0.63
     Robot
    0.63
    Activations Density 0.359%

    No Known Activations