© 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. 10895
    Prev
    Next
    INDEX
    Explanations

    terms related to non-profit organizations or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to non-profit organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     flush
    -0.81
     tack
    -0.80
     lav
    -0.72
     touch
    -0.69
     digging
    -0.68
     gut
    -0.67
     rush
    -0.67
     bricks
    -0.67
     trooper
    -0.67
     heart
    -0.66
    POSITIVE LOGITS
     Non
    2.94
    Non
    1.86
     NON
    1.34
     Semi
    1.15
     Female
    1.06
     Negative
    1.06
     Minor
    1.02
     Same
    1.01
     Partial
    1.01
    non
    1.01
    Activations Density 0.021%

    No Known Activations