© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17169
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or refusal

    oai_token-act-pair · gpt-3.5-turbo

    negation statements, particularly phrases that include "won't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.66
     Floating
    -0.63
    itiz
    -0.60
     linkage
    -0.60
    Kings
    -0.58
     Forums
    -0.58
     Pipeline
    -0.57
    Hardware
    -0.57
     illustration
    -0.56
    edIn
    -0.56
    POSITIVE LOGITS
     necessarily
    0.94
    ardless
    0.85
    itles
    0.81
    apest
    0.80
    ember
    0.79
    rees
    0.78
    payers
    0.76
    urtle
    0.76
    ournament
    0.75
    angular
    0.75
    Activations Density 0.035%

    No Known Activations