© 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. 20094
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and permissions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal agreements and authorization

    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
    Jet
    -0.80
     gigs
    -0.73
    avid
    -0.72
    enes
    -0.72
     Temper
    -0.70
    gaard
    -0.69
    enne
    -0.69
    nik
    -0.69
    Around
    -0.66
    aris
    -0.66
    POSITIVE LOGITS
     applicable
    1.09
     herein
    1.04
     hereby
    1.04
     materially
    1.00
     afore
    0.99
     pursuant
    0.99
     supplemental
    0.95
     thereto
    0.94
     lawful
    0.93
    shall
    0.92
    Activations Density 1.913%

    No Known Activations