© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6656
    Prev
    Next
    INDEX
    Explanations

    mentions of researchers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of researchers or research-related roles

    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
    emption
    -0.59
    guns
    -0.59
    ouston
    -0.58
    illes
    -0.57
    inces
    -0.57
     impe
    -0.57
    Interstitial
    -0.56
    tons
    -0.56
     yards
    -0.56
    thora
    -0.56
    POSITIVE LOGITS
     researcher
    3.52
     researchers
    2.31
    earcher
    2.12
     scientist
    2.08
     biologist
    1.93
     investigator
    1.93
    Researchers
    1.92
     Researchers
    1.92
     scholar
    1.84
     lecturer
    1.75
    Activations Density 0.015%

    No Known Activations