© 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. 3172
    Prev
    Next
    INDEX
    Explanations

    words related to magical spells and incantations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to magical spells and spell-casting

    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
    udeau
    -0.74
    Reviewer
    -0.73
    algia
    -0.72
     Wem
    -0.69
     Cheong
    -0.68
    phia
    -0.67
    psey
    -0.66
    pheus
    -0.64
    ublic
    -0.63
     Alto
    -0.63
    POSITIVE LOGITS
    casting
    1.50
    caster
    1.50
    casters
    1.39
    binding
    1.38
     caster
    1.14
    sword
    1.09
    bind
    1.05
    spell
    1.03
    bound
    1.00
    sheet
    1.00
    Activations Density 0.028%

    No Known Activations