© 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. 20376
    Prev
    Next
    INDEX
    Explanations

    videos or mentions of videos in online platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of videos

    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±
    -0.81
    姫
    -0.79
    cffff
    -0.75
     Flavoring
    -0.75
    estial
    -0.75
    merce
    -0.74
    BuyableInstoreAndOnline
    -0.71
    vier
    -0.69
     Rover
    -0.66
    iders
    -0.66
    POSITIVE LOGITS
     clip
    1.36
     clips
    1.23
     footage
    1.18
     uploaded
    1.16
     filmed
    1.13
    clip
    1.02
     mont
    0.97
     taped
    0.92
     tutorials
    0.92
     recordings
    0.91
    Activations Density 0.043%

    No Known Activations