© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8541
    Prev
    Next
    INDEX
    Explanations

    phrases that mention something "real" or related to reality

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "real" in various contexts

    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
    hire
    -0.73
     Supported
    -0.72
    served
    -0.71
    theless
    -0.71
    Ħ¢
    -0.68
    recated
    -0.68
    attr
    -0.68
    ACK
    -0.68
    ilan
    -0.65
    illet
    -0.65
    POSITIVE LOGITS
    isation
    1.21
    ignment
    1.16
     culprit
    1.14
     estate
    1.09
     reason
    0.99
    igning
    0.98
    igned
    0.98
     kicker
    0.97
     McCoy
    0.93
    polit
    0.91
    Activations Density 0.032%

    No Known Activations