© 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. 6067
    Prev
    Next
    INDEX
    Explanations

    phrases that negate or contradict statements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and auxiliary verbs that indicate conditionality or connection between ideas

    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
    HEAD
    -0.67
     Tid
    -0.59
     champ
    -0.57
     Matrix
    -0.57
     Stockholm
    -0.54
    figure
    -0.54
     ven
    -0.53
    piring
    -0.53
    Ax
    -0.52
     bearer
    -0.52
    POSITIVE LOGITS
     nor
    1.54
     consequently
    1.28
     therefore
    1.22
     neither
    1.20
     furthermore
    1.17
     Nor
    1.16
     moreover
    1.11
     hence
    1.07
    nor
    1.04
     thus
    1.01
    Activations Density 0.352%

    No Known Activations