© 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. 16437
    Prev
    Next
    INDEX
    Explanations

    terms related to dealing with various situations or issues

    oai_token-act-pair · gpt-3.5-turbo
    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
     RS
    -0.60
     Kappa
    -0.60
    cul
    -0.60
    iesta
    -0.60
     Camp
    -0.59
    ization
    -0.59
     Sunrise
    -0.58
     sunrise
    -0.58
     Pic
    -0.58
     Independence
    -0.57
    POSITIVE LOGITS
     dealt
    3.68
     dealing
    1.74
    deal
    1.72
     tackled
    1.60
     handled
    1.60
     deals
    1.49
    Deal
    1.40
     addressed
    1.40
     deal
    1.38
     dodged
    1.36
    Activations Density 0.007%

    No Known Activations