© 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. 0-RES-JB
    11. 2839
    Prev
    Next
    INDEX
    Explanations

    phrases related to the field of pharmacy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "literacy" and "competency."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mist
    -0.65
     FIG
    -0.65
     ref
    -0.64
     once
    -0.63
     KN
    -0.62
     Nare
    -0.61
     Buk
    -0.60
     blind
    -0.59
     opp
    -0.58
     repl
    -0.58
    POSITIVE LOGITS
    acy
    4.72
    acies
    2.54
    ACY
    2.48
    acists
    1.69
    acist
    1.46
    ately
    1.45
    atics
    1.33
    ate
    1.32
    ace
    1.32
    acey
    1.29
    Activations Density 0.006%

    No Known Activations