© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    phrases expressing refusal or opposition

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of refusal

    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
     nonetheless
    -0.71
     nevertheless
    -0.70
    ãĤ¼
    -0.69
    ãĥ¼ãĥĨ
    -0.66
     unmist
    -0.65
    ãĥ¯ãĥ³
    -0.64
     invariably
    -0.64
     swiftly
    -0.64
    senal
    -0.63
     simultaneously
    -0.62
    POSITIVE LOGITS
    hin
    1.34
     fuckin
    1.14
     wanna
    1.11
     deserve
    1.09
     fucking
    1.00
     gonna
    0.95
     belong
    0.92
     condone
    0.92
     exist
    0.91
     EVEN
    0.90
    Activations Density 0.265%

    No Known Activations