© 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. 5570
    Prev
    Next
    INDEX
    Explanations

    quotations or direct speech

    oai_token-act-pair · gpt-3.5-turbo

    the presence of quoted speech or dialogue

    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
    ãĥ¼ãĥ«
    -0.73
     committed
    -0.67
     discriminated
    -0.65
     overlooked
    -0.64
     mapping
    -0.64
     swat
    -0.63
     neglected
    -0.62
     envy
    -0.62
     lining
    -0.61
     jerk
    -0.61
    POSITIVE LOGITS
    Interstitial
    1.00
    Cause
    0.87
    Hom
    0.81
     '[
    0.79
    ',
    0.79
    Mech
    0.78
    yss
    0.78
    Medic
    0.78
    We
    0.77
    Muslim
    0.76
    Activations Density 0.026%

    No Known Activations