© 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. 7-RES-JB
    11. 13451
    Prev
    Next
    INDEX
    Explanations

    discrepancies between appearance or assertion and reality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight the contrast between perception and reality

    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
    uyomi
    -0.70
    inel
    -0.65
    erity
    -0.63
    luster
    -0.63
    rosso
    -0.62
     EDITION
    -0.62
    aunted
    -0.62
    ador
    -0.61
    tackle
    -0.60
    iculty
    -0.60
    POSITIVE LOGITS
     indeed
    0.90
     untrue
    0.81
     actually
    0.79
     meant
    0.77
     intended
    0.76
     true
    0.72
    actually
    0.71
    REDACTED
    0.70
     existed
    0.68
     factual
    0.68
    Activations Density 0.973%

    No Known Activations