Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 997
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names, particularly "Curtis" and "Sears"

    oai_token-act-pair · gpt-3.5-turbo

    specific names, particularly of individuals involved in notable events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saline
    -0.84
    iosis
    -0.83
     disarm
    -0.82
    sylvania
    -0.82
    cious
    -0.81
    eals
    -0.80
    oÄŁ
    -0.79
    agan
    -0.79
    iod
    -0.77
    ulsion
    -0.77
    POSITIVE LOGITS
     Curtis
    0.88
     Compton
    0.86
    crow
    0.84
     Crosby
    0.79
    UAL
    0.78
     Bowie
    0.70
     Sparks
    0.69
     Sph
    0.69
    creen
    0.67
     Hook
    0.67
    Activations Density 0.016%

    No Known Activations