© 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. 10-RES-JB
    11. 11131
    Prev
    Next
    INDEX
    Explanations

    words related to spokespersons or representatives

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [];
    -0.74
    ised
    -0.70
     Bagg
    -0.69
     steroids
    -0.66
     weighted
    -0.64
     unsustainable
    -0.61
    OUS
    -0.61
     educ
    -0.61
     Ukrain
    -0.60
     bleach
    -0.59
    POSITIVE LOGITS
    men
    2.36
    man
    2.32
    woman
    1.97
    mans
    1.89
    women
    1.84
    manship
    1.84
    people
    1.83
    person
    1.82
    mens
    1.55
    pers
    1.53
    Activations Density 0.182%

    No Known Activations