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. 4-RES-JB
    6. 18848
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Pekka" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ek"

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

    No Comments

    Negative Logits
    ACTED
    -0.79
    ãĤ¤
    -0.67
     AMERICA
    -0.67
    ãĥĩãĤ£
    -0.66
    ãĥ¼ãĥĨ
    -0.63
     canned
    -0.63
    ãģĤ
    -0.62
    FACE
    -0.62
     contrace
    -0.62
     Bland
    -0.62
    POSITIVE LOGITS
    nown
    1.36
    kers
    1.07
    enstein
    1.04
    owitz
    1.03
    anism
    1.01
    eker
    1.00
    oop
    0.96
    kies
    0.96
    ansas
    0.95
    yll
    0.94
    Activations Density 0.017%

    No Known Activations