© 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. 6744
    Prev
    Next
    INDEX
    Explanations

    references to downloadable content (DLC)

    oai_token-act-pair · gpt-3.5-turbo

    references to downloadable content (DLC)

    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
    Hamilton
    -0.74
    ouston
    -0.72
    omed
    -0.65
    oward
    -0.65
    eor
    -0.61
    onder
    -0.60
    Mat
    -0.60
    ï¸
    -0.60
     Meyer
    -0.60
    iss
    -0.60
    POSITIVE LOGITS
     DLC
    3.82
     downloadable
    1.52
     DRM
    1.20
     expansions
    1.15
     multiplayer
    1.15
     playthrough
    1.15
     Multiplayer
    1.12
     playable
    1.09
     Borderlands
    1.09
     sequels
    1.03
    Activations Density 0.020%

    No Known Activations