© 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. 17284
    Prev
    Next
    INDEX
    Explanations

    contractions with negations

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of inability or 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
     newcom
    -0.76
    anwhile
    -0.74
     princ
    -0.72
     gobl
    -0.71
     satell
    -0.65
     referen
    -0.62
     populated
    -0.61
     Powered
    -0.61
     revolving
    -0.61
     juven
    -0.60
    POSITIVE LOGITS
    't
    1.48
    ´
    0.82
    âĶĢâĶĢâĶĢâĶĢ
    0.82
    itely
    0.82
    n
    0.81
    ÃŃ
    0.81
    Õ
    0.79
    probably
    0.79
    âĤ¬
    0.78
    bare
    0.78
    Activations Density 0.032%

    No Known Activations