© 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. 8-RES-JB
    11. 1873
    Prev
    Next
    INDEX
    Explanations

    instances where something appears to be something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe appearances or perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iband
    -0.86
    anwhile
    -0.71
    lished
    -0.70
    gard
    -0.70
    otom
    -0.70
     withd
    -0.70
    ellen
    -0.70
    banks
    -0.70
    rer
    -0.69
    vez
    -0.68
    POSITIVE LOGITS
     innocuous
    0.81
     fireworks
    0.64
     insur
    0.64
     random
    0.60
     accidental
    0.60
     derogatory
    0.59
     Goo
    0.59
     unintentional
    0.58
     spurious
    0.58
     authentic
    0.58
    Activations Density 0.088%

    No Known Activations