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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 92
    Prev
    Next
    INDEX
    Explanations

    words related to geographical basins

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical regions and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.89
    ammed
    -0.76
     srf
    -0.76
    haw
    -0.70
    ramer
    -0.69
    otos
    -0.69
    reading
    -0.68
    ivated
    -0.67
    inel
    -0.67
    apes
    -0.67
    POSITIVE LOGITS
     Basin
    1.16
     basin
    1.09
    ctr
    0.79
    zinski
    0.75
    forth
    0.65
     Miko
    0.63
     Scrolls
    0.63
     Tribune
    0.62
     Amph
    0.62
     Springs
    0.62
    Activations Density 0.022%

    No Known Activations