© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5348
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames or handles

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical identifiers or codes, particularly in web links and social media profiles

    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
     commuting
    -0.69
     felon
    -0.68
     accrued
    -0.68
     caring
    -0.65
     stuffing
    -0.64
     discern
    -0.63
     immedi
    -0.62
     distances
    -0.60
     condol
    -0.60
     conscience
    -0.59
    POSITIVE LOGITS
    Cu
    1.19
    CN
    1.18
    yk
    1.18
    zx
    1.18
    OX
    1.18
    yip
    1.17
    FK
    1.16
    nv
    1.16
    Eh
    1.16
    DN
    1.14
    Activations Density 0.036%

    No Known Activations