© 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. 11-RES-JB
    11. 22492
    Prev
    Next
    INDEX
    Explanations

    video-related keywords and phrases

    oai_token-act-pair · gpt-3.5-turbo

    content related to video titles or video watch prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kowski
    -0.62
    schild
    -0.61
    heit
    -0.61
    adem
    -0.57
    wagon
    -0.57
    umenthal
    -0.53
    anka
    -0.52
     Sparrow
    -0.52
    lain
    -0.51
    acea
    -0.51
    POSITIVE LOGITS
     MUST
    1.38
    must
    0.78
    Must
    0.75
     Must
    0.71
     WATCH
    0.66
     SHOULD
    0.63
     must
    0.63
     Became
    0.62
    Spawn
    0.61
     MAY
    0.60
    Activations Density 0.026%

    No Known Activations