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

    Neuronpedia

    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. 7-RES-JB
    11. 12570
    Prev
    Next
    INDEX
    Explanations

    computer programming terminology, specifically related to scripting languages and software development

    oai_token-act-pair · gpt-3.5-turbo

    elements related to various entities and classifications in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Entered
    -0.91
     Diablo
    -0.68
     Hutchinson
    -0.68
     dred
    -0.58
     Sussex
    -0.57
     bidder
    -0.56
     awoken
    -0.56
    obyl
    -0.56
     fumes
    -0.54
     UNCLASSIFIED
    -0.54
    POSITIVE LOGITS
    NAS
    0.65
    cap
    0.64
    ode
    0.63
    ipal
    0.63
    parent
    0.63
    paren
    0.61
    Tokens
    0.61
    çķ
    0.61
    Adult
    0.61
    arten
    0.61
    Activations Density 0.699%

    No Known Activations