© 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. 6-RES-JB
    11. 19725
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, rankings, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to voting or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brakes
    -0.63
    apego
    -0.62
    asu
    -0.56
    umbnails
    -0.55
    ettel
    -0.55
    ient
    -0.54
    obyl
    -0.52
     <[
    -0.51
    ÃįÃį
    -0.51
    hran
    -0.50
    POSITIVE LOGITS
     guise
    0.86
     vicinity
    0.82
     contexts
    0.81
     context
    0.73
     territory
    0.72
     precincts
    0.71
     manner
    0.71
     nutshell
    0.68
     mode
    0.68
     increments
    0.66
    Activations Density 1.447%

    No Known Activations