© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    phrases related to positions or titles within an organization or structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coordinators or individuals in leadership positions

    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
     Judicial
    -0.72
    cig
    -0.71
     seiz
    -0.70
     notch
    -0.68
     trem
    -0.65
     Moderate
    -0.65
     este
    -0.64
     Vie
    -0.64
    rig
    -0.62
     heel
    -0.62
    POSITIVE LOGITS
    inator
    4.21
    inators
    3.21
    inatory
    1.08
    ahead
    1.00
    enable
    0.97
    present
    0.95
    creator
    0.95
    opher
    0.95
     Banner
    0.94
    rower
    0.93
    Activations Density 0.040%

    No Known Activations