© 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. 11906
    Prev
    Next
    INDEX
    Explanations

    mentions of significant discoveries or findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "discovery."

    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
    overe
    -0.76
    annis
    -0.76
    redited
    -0.75
    osuke
    -0.74
    uffs
    -0.69
    eworks
    -0.68
    attery
    -0.67
    asus
    -0.67
    oiler
    -0.66
    owler
    -0.66
    POSITIVE LOGITS
     Flavoring
    0.80
    éļ
    0.72
    ource
    0.71
    Reviewed
    0.71
    acly
    0.71
    iveness
    0.71
    ãĥĭ
    0.70
     Primordial
    0.70
    ļéĨĴ
    0.68
    使
    0.67
    Activations Density 0.041%

    No Known Activations