© 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. 2-RES-JB
    11. 12754
    Prev
    Next
    INDEX
    Explanations

    words related to magic or casting spells

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spell" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.85
    algia
    -0.82
    pheus
    -0.79
    guyen
    -0.72
    ribut
    -0.71
     Roosevelt
    -0.70
    gewater
    -0.69
    ometown
    -0.68
    Reviewer
    -0.67
    agonists
    -0.67
    POSITIVE LOGITS
    caster
    1.07
    casters
    1.05
     spells
    1.03
     spell
    1.02
    casting
    1.00
    binding
    0.92
    Spell
    0.84
    mers
    0.83
     spelled
    0.83
    ings
    0.81
    Activations Density 0.004%

    No Known Activations