© 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. 10-RES-JB
    11. 23444
    Prev
    Next
    INDEX
    Explanations

    words related to proper names, initials, and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zai
    -0.81
    eers
    -0.79
    eer
    -0.78
    hold
    -0.77
    rer
    -0.68
    initialized
    -0.67
    pron
    -0.66
    icating
    -0.65
    icates
    -0.65
     è£ıç
    -0.63
    POSITIVE LOGITS
    FO
    1.19
    BC
    1.15
    LC
    1.15
    FC
    1.13
    WD
    1.12
    KN
    1.12
    VI
    1.11
    AD
    1.10
    ND
    1.10
    OC
    1.10
    Activations Density 0.111%

    No Known Activations