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. 3-RES-JB
    6. 13969
    Prev
    Next
    INDEX
    Explanations

    locations, specifically places related to legal or investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    geographical names, specifically those related to locations in Florida and California

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.75
    IPS
    -0.73
    ãĤ¯
    -0.68
    NK
    -0.67
    Mach
    -0.67
    VALUE
    -0.66
    PATH
    -0.65
    winner
    -0.65
    ä¹
    -0.65
    ACTION
    -0.64
    POSITIVE LOGITS
    quished
    0.81
    abama
    0.76
    erville
    0.72
     Springs
    0.72
     mayoral
    0.72
     Harbor
    0.72
     2024
    0.71
     suburbs
    0.71
    hyde
    0.71
     Heights
    0.71
    Activations Density 0.056%

    No Known Activations