© 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. 0-RES-JB
    11. 19998
    Prev
    Next
    INDEX
    Explanations

    references to physical attachments or physical objects that are attached

    oai_token-act-pair · gpt-3.5-turbo

    words related to attachments and connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carlos
    -0.71
    YN
    -0.68
    yan
    -0.67
    ÃŃ
    -0.66
    izz
    -0.65
     Clin
    -0.63
     Pyramid
    -0.63
     Moran
    -0.63
    Cos
    -0.62
    fair
    -0.62
    POSITIVE LOGITS
     attachment
    4.06
     attachments
    3.44
    Attach
    1.95
     attached
    1.81
     attach
    1.78
    achment
    1.55
     attaching
    1.55
     attaches
    1.53
     detachment
    1.45
    attach
    1.43
    Activations Density 0.019%

    No Known Activations