© 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. 24369
    Prev
    Next
    INDEX
    Explanations

    specific items or actions of interest placed within a larger context

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and items related to placement or organization

    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
     immensely
    -0.60
     ende
    -0.59
    ranged
    -0.59
     cryst
    -0.58
    adjusted
    -0.58
     conduc
    -0.55
     reluct
    -0.55
    ruciating
    -0.55
    etheless
    -0.54
    normal
    -0.53
    POSITIVE LOGITS
     onto
    1.45
     into
    1.40
     Into
    1.11
    into
    0.97
     INTO
    0.96
     squarely
    0.96
     atop
    0.87
     inside
    0.86
     aside
    0.84
     prominently
    0.82
    Activations Density 0.375%

    No Known Activations