© 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. 20253
    Prev
    Next
    INDEX
    Explanations

    names of political figures or leaders

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    PsyNetMessage
    -0.87
    Discover
    -0.76
     Scrolls
    -0.74
    acters
    -0.71
    azard
    -0.70
    negie
    -0.68
    inav
    -0.66
     Triangle
    -0.66
     reproduction
    -0.65
     automate
    -0.65
    POSITIVE LOGITS
     presiding
    1.22
     unpopular
    1.19
     campaigning
    1.18
     sworn
    1.15
     appointed
    1.14
     impe
    1.13
     elected
    1.10
     assassinated
    1.10
     chairman
    1.07
     briefed
    1.07
    Activations Density 0.259%

    No Known Activations