© 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. 2799
    Prev
    Next
    INDEX
    Explanations

    prompts asking the reader to verify that they are not a robot

    oai_token-act-pair · gpt-3.5-turbo
    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
    76561
    -0.71
    itar
    -0.67
     Poc
    -0.63
     Sapp
    -0.60
     Brun
    -0.59
     Bethesda
    -0.59
     Brist
    -0.59
    talk
    -0.58
    ARC
    -0.57
     Carib
    -0.57
    POSITIVE LOGITS
     verify
    0.90
    asse
    0.78
    %]
    0.76
     enable
    0.73
     Subscribe
    0.72
     arming
    0.69
    ete
    0.67
     Sign
    0.66
     SIGN
    0.64
     subscribe
    0.63
    Activations Density 0.011%

    No Known Activations