© 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. 2-RES-JB
    11. 12891
    Prev
    Next
    INDEX
    Explanations

    acronyms related to organizations or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lets
    -0.72
     Requ
    -0.72
     istg
    -0.70
    onen
    -0.67
     Oo
    -0.66
     Allaah
    -0.63
     cir
    -0.61
    lighting
    -0.61
    give
    -0.60
     Raven
    -0.60
    POSITIVE LOGITS
    HS
    0.89
    FU
    0.86
    Ds
    0.83
    DERR
    0.81
    xual
    0.81
    SE
    0.80
    DEF
    0.79
    olicy
    0.79
    dit
    0.77
    OF
    0.77
    Activations Density 0.162%

    No Known Activations