© 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. 6-RES-JB
    11. 15268
    Prev
    Next
    INDEX
    Explanations

    sentences containing statements or quotes

    oai_token-act-pair · gpt-3.5-turbo

    statements and assertions about what people have said

    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
    equipped
    -0.77
    Mech
    -0.67
    gart
    -0.65
    stru
    -0.63
    shoot
    -0.63
     replen
    -0.63
     Ley
    -0.62
     Entered
    -0.61
    riot
    -0.61
    ritional
    -0.61
    POSITIVE LOGITS
     aloud
    0.96
     goodbye
    0.90
     uttered
    0.80
     about
    0.75
     loudly
    0.73
    escription
    0.71
    terday
    0.70
     beforehand
    0.69
    INGS
    0.68
     afterwards
    0.67
    Activations Density 0.064%

    No Known Activations