© 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. 14135
    Prev
    Next
    INDEX
    Explanations

    Keywords related to images or photographs

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs and photo-related content

    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
    ensable
    -0.77
    ciating
    -0.73
    cair
    -0.73
    rane
    -0.71
    steen
    -0.70
    orse
    -0.69
    urous
    -0.67
    inence
    -0.66
    ngth
    -0.66
    _-
    -0.66
    POSITIVE LOGITS
    journal
    1.43
     gallery
    1.16
    ynthesis
    1.07
     album
    1.05
    album
    1.03
     galleries
    1.03
     shoot
    0.99
     essay
    0.97
     illustration
    0.97
    ynt
    0.96
    Activations Density 0.041%

    No Known Activations