© 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. 24055
    Prev
    Next
    INDEX
    Explanations

    social media sharing prompts or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    references to sharing content or articles

    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
    Ĭ±
    -0.78
     departures
    -0.66
    »Ĵ
    -0.63
     exceptions
    -0.61
     Beasts
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
    Ĥ
    -0.56
    irlfriend
    -0.55
    ħĭ
    -0.55
    Īè
    -0.55
    POSITIVE LOGITS
    Tweet
    1.02
    edin
    1.00
     Tweet
    0.84
     bookmark
    0.81
     infographic
    0.76
     ARTICLE
    0.75
    asta
    0.73
    !:
    0.71
     inspires
    0.71
    Pinterest
    0.70
    Activations Density 0.037%

    No Known Activations