© 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. 7-RES-JB
    11. 23538
    Prev
    Next
    INDEX
    Explanations

    words related to ownership or investment interest

    oai_token-act-pair · gpt-3.5-turbo

    references to "stake" in various contexts related to ownership and investment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICA
    -0.79
    eric
    -0.77
    audi
    -0.76
    pmwiki
    -0.75
    ica
    -0.72
    uters
    -0.70
    anguage
    -0.70
    icz
    -0.68
    issance
    -0.67
    ysis
    -0.67
    POSITIVE LOGITS
    holder
    1.53
     stake
    1.06
    holders
    1.02
     stakes
    0.95
    pole
    0.84
    iffs
    0.75
    rament
    0.72
    holding
    0.71
     crane
    0.71
    ware
    0.67
    Activations Density 0.036%

    No Known Activations