Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 14496
    Prev
    Next
    INDEX
    Explanations

    conjuring or conjuring-related words and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to conjuring or magical actions and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    board
    -0.78
    WARE
    -0.70
    boards
    -0.69
     Pref
    -0.68
    boarding
    -0.64
     waivers
    -0.60
     spaced
    -0.60
     Hayden
    -0.60
     SAN
    -0.59
     Ferry
    -0.59
    POSITIVE LOGITS
    unct
    1.57
    ugal
    1.47
    uncture
    1.39
    unctions
    1.31
    ug
    1.30
    urer
    1.27
    urers
    1.25
    oint
    1.23
    uration
    1.16
    urations
    1.15
    Activations Density 0.131%

    No Known Activations