© 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. 8846
    Prev
    Next
    INDEX
    Explanations

    mentions of predecessors

    oai_token-act-pair · gpt-3.5-turbo

    references to past leaders or predecessors

    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
    alle
    -0.68
    hma
    -0.66
     Abyssal
    -0.66
    Bron
    -0.65
    agra
    -0.65
    swing
    -0.64
    owler
    -0.64
    ouring
    -0.64
    bra
    -0.62
     Shore
    -0.61
    POSITIVE LOGITS
     predecessor
    1.33
     predecessors
    1.10
    cules
    0.90
     successor
    0.88
    etheless
    0.82
     Tad
    0.77
     incarn
    0.74
     counterpart
    0.74
    utive
    0.70
    hesis
    0.70
    Activations Density 0.008%

    No Known Activations