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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 5428
    Prev
    Next
    INDEX
    Explanations

    the word "Al" followed by a numeric value, potentially indicating a name or a specific label within a context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "al" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olicy
    -0.82
    ãĥ¼ãĥĨãĤ£
    -0.74
     sterling
    -0.71
    éĹĺ
    -0.71
    FFER
    -0.71
    æĸ¹
    -0.68
     Chaser
    -0.67
    CRIP
    -0.66
    åŃIJ
    -0.65
    ession
    -0.65
    POSITIVE LOGITS
     Pradesh
    1.15
    axy
    1.14
    ibaba
    1.10
    aska
    1.09
    abama
    1.08
    iland
    1.05
    anguage
    1.05
    gebra
    1.05
    ogical
    1.02
    gorith
    1.01
    Activations Density 0.054%

    No Known Activations