© 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. 2878
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person or entity, such as "Doc Washburn"

    oai_token-act-pair · gpt-3.5-turbo

    names or mentions of individuals, particularly in a specific context

    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
     footage
    -0.76
     span
    -0.69
     advance
    -0.64
     clip
    -0.64
     passage
    -0.62
     seniors
    -0.61
     clips
    -0.61
     marches
    -0.60
     ESP
    -0.60
     mushroom
    -0.60
    POSITIVE LOGITS
    âĢ
    1.70
    ãĤ¨ãĥ«
    1.05
    âĿ
    0.97
    âľ
    0.96
    ï¸
    0.95
    borgh
    0.95
    âĺ
    0.94
    HCR
    0.94
    âĸº
    0.91
    Always
    0.89
    Activations Density 0.000%

    No Known Activations