© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3359
    Prev
    Next
    INDEX
    Explanations

    action verbs related to data input and processing

    oai_token-act-pair · gpt-3.5-turbo

    instances of data-related issues or user input mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overse
    -0.65
     wiser
    -0.65
     harsher
    -0.60
     successors
    -0.58
     jurisdiction
    -0.56
     jails
    -0.55
     conferences
    -0.55
     nearer
    -0.55
     sharper
    -0.55
     organising
    -0.55
    POSITIVE LOGITS
    ðŁĺ
    0.58
    acters
    0.57
    00000000
    0.56
    ¼
    0.56
    igible
    0.55
    poon
    0.53
     mirac
    0.53
    ¢
    0.52
    existent
    0.52
    á¹
    0.52
    Activations Density 0.935%

    No Known Activations