© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13241
    Prev
    Next
    INDEX
    Explanations

    words related to positive attributes or qualities, specifically terms related to charm

    oai_token-act-pair · gpt-3.5-turbo

    references to charm and its variations in various contexts

    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
    sections
    -0.76
     Related
    -0.75
    NAS
    -0.74
    apa
    -0.73
    FO
    -0.73
    β
    -0.64
    afa
    -0.64
     streamed
    -0.63
    ETF
    -0.63
    ors
    -0.63
    POSITIVE LOGITS
     charm
    4.32
     charms
    3.02
     Charm
    2.45
     charming
    1.43
     charisma
    1.43
     lure
    1.27
     enchant
    1.18
     enchantment
    1.18
     humour
    1.10
     vibe
    1.08
    Activations Density 0.025%

    No Known Activations