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. 9-RES-JB
    6. 8497
    Prev
    Next
    INDEX
    Explanations

    quotes or statements attributed to individuals, particularly with names that include prefixes like "O'"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isode
    -0.68
     Libyan
    -0.63
     copy
    -0.62
     screen
    -0.61
    redients
    -0.61
     semic
    -0.60
     venture
    -0.60
     JC
    -0.60
     RESP
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.59
    POSITIVE LOGITS
    ĸļ
    1.32
    ¡
    1.30
    ¬
    1.28
    ħ
    1.25
    Ń
    1.22
    ³
    1.21
    ı
    1.21
    į
    1.20
    º
    1.19
    £
    1.19
    Activations Density 0.133%

    No Known Activations