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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 19375
    Prev
    Next
    INDEX
    Explanations

    words related to conjuring or summoning things or ideas

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "conjure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TPS
    -0.74
     Goo
    -0.73
    OPLE
    -0.73
     Carnegie
    -0.70
    DragonMagazine
    -0.70
    WARE
    -0.69
    abwe
    -0.68
    iary
    -0.66
    iology
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
    unct
    1.15
     conj
    1.09
    uncture
    1.08
    ugal
    1.05
    uration
    1.04
    oked
    0.93
    ure
    0.90
    unctions
    0.89
    ured
    0.88
    urous
    0.87
    Activations Density 0.008%

    No Known Activations