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. 7-RES-JB
    6. 24344
    Prev
    Next
    INDEX
    Explanations

    mentions of the gaming console "PS9"

    oai_token-act-pair · gpt-3.5-turbo

    references to PlayStation gaming consoles

    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
    butt
    -0.89
    glers
    -0.69
    gling
    -0.67
     grounds
    -0.65
     adm
    -0.65
    ãĥ¼ãĤ¯
    -0.65
     Sloven
    -0.63
     ç¥ŀ
    -0.63
    ãĥĥ
    -0.62
    Reviewer
    -0.62
    POSITIVE LOGITS
    atile
    1.12
    FK
    0.96
    RP
    0.95
    Ħ¢
    0.90
    UV
    0.89
    ilon
    0.87
    ullivan
    0.86
    GS
    0.86
    weet
    0.86
    HT
    0.85
    Activations Density 0.017%

    No Known Activations