© 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. 18870
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "John" or "Johann" at the end

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a delimiter or end-of-text marker

    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
    rets
    -0.76
    mine
    -0.69
    BuyableInstoreAndOnline
    -0.67
    SourceFile
    -0.66
     accum
    -0.65
    rero
    -0.64
     Flam
    -0.63
    riers
    -0.61
    âĹ¼
    -0.61
     contrace
    -0.60
    POSITIVE LOGITS
    vironment
    1.27
    ocide
    0.97
    ihil
    0.95
    aturally
    0.93
    ancial
    0.93
    swer
    0.93
    iece
    0.92
    ovation
    0.90
    emonic
    0.89
    igans
    0.89
    Activations Density 0.030%

    No Known Activations