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. 4-RES-JB
    6. 17852
    Prev
    Next
    INDEX
    Explanations

    mentions of "CL" codes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "CL" followed by numerical values or contextually relevant information

    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
    ãĥĦ
    -0.93
    ãĥ´ãĤ¡
    -0.82
    ãĤ®
    -0.80
    tale
    -0.79
    ãĤ¹ãĥĪ
    -0.78
    spect
    -0.76
    hide
    -0.76
    tackle
    -0.76
    ãĥĥ
    -0.75
    catch
    -0.75
    POSITIVE LOGITS
    OSED
    1.07
    INTON
    1.05
    IENT
    0.97
    OCK
    0.96
    OTH
    0.94
    avier
    0.88
    ANN
    0.87
    opez
    0.85
    AMP
    0.81
    isters
    0.81
    Activations Density 0.003%

    No Known Activations