© 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. 16216
    Prev
    Next
    INDEX
    Explanations

    dates, times, quantities, and notable numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to social media and public figures

    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
    again
    -0.70
    Secondly
    -0.68
     secondly
    -0.66
     therefore
    -0.63
     however
    -0.62
     deteriorating
    -0.62
     weaker
    -0.62
     weakened
    -0.60
     worsened
    -0.60
     decreased
    -0.60
    POSITIVE LOGITS
     salute
    0.76
     flick
    0.70
     playlist
    0.69
     quiz
    0.66
     gle
    0.65
    *.
    0.63
     cue
    0.62
     nab
    0.62
     thw
    0.62
     stocked
    0.61
    Activations Density 1.130%

    No Known Activations