© 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. 9-RES-JB
    11. 1033
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming keywords

    oai_token-act-pair · gpt-3.5-turbo

    empty sections or gaps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breaching
    -0.58
     TBA
    -0.56
    enegger
    -0.54
     undermin
    -0.54
    asca
    -0.54
     judging
    -0.54
     Olympia
    -0.53
    aturdays
    -0.53
     hubs
    -0.53
     Indust
    -0.53
    POSITIVE LOGITS
     :=
    0.97
     isEnabled
    0.96
    operator
    0.91
    array
    0.90
    Array
    0.89
    actionDate
    0.88
    {
    0.88
    seq
    0.86
    String
    0.86
    func
    0.85
    Activations Density 0.289%

    No Known Activations