© 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. 1-RES-JB
    11. 24139
    Prev
    Next
    INDEX
    Explanations

    precise verbs related to observation or understanding

    oai_token-act-pair · gpt-3.5-turbo

    words related to perception and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.70
    OH
    -0.70
    rush
    -0.69
    USE
    -0.66
    rera
    -0.64
    hibit
    -0.63
    atro
    -0.62
    raid
    -0.61
    ´
    -0.61
    BRE
    -0.61
    POSITIVE LOGITS
     discern
    1.02
    ible
    0.88
    hest
    0.86
     glim
    0.83
    hent
    0.82
    iban
    0.82
    wered
    0.82
    iour
    0.79
    ibly
    0.79
    smanship
    0.78
    Activations Density 0.015%

    No Known Activations