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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 21288
    Prev
    Next
    INDEX
    Explanations

    the name "Logan" and related variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific characters, particularly 'Logan' and 'Wolverine.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minist
    -0.81
    guided
    -0.74
    ibel
    -0.70
    ramid
    -0.70
    ktop
    -0.69
    ummer
    -0.68
    placed
    -0.68
    apers
    -0.68
     dstg
    -0.68
    tops
    -0.68
    POSITIVE LOGITS
     Logan
    0.99
    istical
    0.83
    ously
    0.83
    culosis
    0.81
    ãĤĬ
    0.77
     Lucky
    0.75
     Showdown
    0.74
    azines
    0.70
     Ness
    0.70
     Dull
    0.70
    Activations Density 0.059%

    No Known Activations