© 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. 10-RES-JB
    11. 20601
    Prev
    Next
    INDEX
    Explanations

    measurements presented as percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to rarity and uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hiber
    -0.58
     dotted
    -0.58
     minus
    -0.57
    abase
    -0.57
     grid
    -0.56
     ageing
    -0.55
     posting
    -0.55
     thous
    -0.54
     endif
    -0.53
    ipedia
    -0.52
    POSITIVE LOGITS
    dayName
    0.64
    tained
    0.62
    pite
    0.61
     Partnership
    0.60
    ilic
    0.59
     Warden
    0.59
    voy
    0.58
    iser
    0.58
    rentice
    0.58
     Jury
    0.57
    Activations Density 0.148%

    No Known Activations