© 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. 11-RES-JB
    11. 7000
    Prev
    Next
    INDEX
    Explanations

    former positions or titles held by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to former roles or titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cation
    -0.60
    suits
    -0.56
    ispers
    -0.55
    ayers
    -0.54
    enges
    -0.53
    alties
    -0.53
    ouls
    -0.53
    hops
    -0.52
    elight
    -0.52
    omes
    -0.52
    POSITIVE LOGITS
     drummer
    0.87
     pastor
    0.87
     guitarist
    0.86
     chef
    0.86
     lieutenant
    0.84
     biologist
    0.83
     sergeant
    0.82
     poet
    0.82
     treasurer
    0.82
     editor
    0.82
    Activations Density 0.422%

    No Known Activations