© 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. 9-RES-JB
    11. 5288
    Prev
    Next
    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Twitter and prompts to follow users on the platform

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moot
    -0.64
    erella
    -0.62
    gregation
    -0.61
    vernment
    -0.61
    cision
    -0.58
    rans
    -0.58
     ordinance
    -0.57
     circumcision
    -0.57
     Croat
    -0.56
     mids
    -0.55
    POSITIVE LOGITS
     (@
    1.10
     @
    1.00
     Follow
    0.81
     Username
    0.77
    Tweet
    0.76
     ðŁij
    0.76
    Follow
    0.75
     "@
    0.75
     hashtag
    0.74
    ðŁ
    0.72
    Activations Density 0.021%

    No Known Activations