© 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. 0-RES-JB
    11. 11514
    Prev
    Next
    INDEX
    Explanations

    terms related to being firm or assertive in a statement

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal or formal definitions and statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hop
    -0.68
     funn
    -0.63
     rejection
    -0.62
     postp
    -0.61
     rep
    -0.59
     prep
    -0.57
     cheer
    -0.57
     Reach
    -0.56
     sponsors
    -0.56
     donation
    -0.55
    POSITIVE LOGITS
    ined
    4.47
    ining
    2.82
    ines
    2.13
    iners
    1.85
    iner
    1.74
    INE
    1.69
    ine
    1.65
    inated
    1.58
    inement
    1.55
    inery
    1.54
    Activations Density 0.008%

    No Known Activations