© 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. 16385
    Prev
    Next
    INDEX
    Explanations

    proper names related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper names of people and organizations

    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
    ocard
    -0.87
    ancers
    -0.80
    visor
    -0.79
    ikers
    -0.78
    psons
    -0.74
    Score
    -0.74
    onder
    -0.72
    arm
    -0.72
    ancer
    -0.71
     Antar
    -0.69
    POSITIVE LOGITS
     Barnett
    1.33
    Barn
    0.71
     McMahon
    0.69
     Abbott
    0.69
     Ingram
    0.69
    TAIN
    0.69
     McGee
    0.67
     Pax
    0.67
     mandates
    0.67
    rules
    0.66
    Activations Density 0.017%

    No Known Activations