© 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. 23579
    Prev
    Next
    INDEX
    Explanations

    actions related to looking or observing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "look" and its variations

    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
    accompan
    -0.66
    EStreamFrame
    -0.63
    ricular
    -0.61
    MQ
    -0.60
    ä¹
    -0.60
     Trad
    -0.60
    elsen
    -0.60
    learning
    -0.60
    iHUD
    -0.59
    rss
    -0.58
    POSITIVE LOGITS
     suspicious
    0.78
     alike
    0.76
     ashamed
    0.76
     suspic
    0.75
     favorably
    0.74
     bored
    0.72
     puzzled
    0.71
     invincible
    0.71
     incred
    0.70
     embarrassed
    0.70
    Activations Density 0.055%

    No Known Activations