© 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. 4-RES-JB
    11. 3626
    Prev
    Next
    INDEX
    Explanations

    social media handles or usernames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter handles

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

    No Comments

    Negative Logits
    emonium
    -0.73
     Vie
    -0.70
     Rite
    -0.69
     Reincarn
    -0.69
     ordinance
    -0.67
     choir
    -0.67
    erella
    -0.67
     Bradford
    -0.67
     frig
    -0.66
     pneum
    -0.66
    POSITIVE LOGITS
    realDonaldTrump
    1.11
    #$
    1.07
    @@@@@@@@
    1.00
    facebook
    0.98
    TAG
    0.94
    twitter
    0.89
    groups
    0.87
    nat
    0.87
    link
    0.85
    wik
    0.85
    Activations Density 0.021%

    No Known Activations