© 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. 10724
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or sources of origin

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups or participants from different regions or backgrounds

    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
    potion
    -0.76
    luck
    -0.67
    ratulations
    -0.67
    manac
    -0.67
    omy
    -0.65
    staking
    -0.65
    henko
    -0.64
    Order
    -0.64
    mere
    -0.64
    tes
    -0.63
    POSITIVE LOGITS
     across
    1.44
     abroad
    1.34
     afar
    1.30
     diverse
    1.17
     disparate
    1.13
     around
    1.13
     everywhere
    1.10
     various
    1.10
     Across
    1.09
     different
    1.08
    Activations Density 0.137%

    No Known Activations