© 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. 8-RES-JB
    11. 22463
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and components related to data structures and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tai
    -0.68
     Britann
    -0.67
     Schne
    -0.65
     Schwe
    -0.65
     Durham
    -0.64
     Charity
    -0.64
     Buch
    -0.63
     Crab
    -0.62
     reluct
    -0.62
     earthqu
    -0.62
    POSITIVE LOGITS
    _
    1.48
    __
    1.24
    ()
    1.21
    Enabled
    1.09
    ="
    1.05
    _-_
    1.05
     &&
    1.04
     +=
    1.02
    =
    1.02
    ();
    1.01
    Activations Density 0.178%

    No Known Activations