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. 4572
    Prev
    Next
    INDEX
    Explanations

    high-level meetings or discussions between important figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "met" in various contexts

    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
    trop
    -0.73
    argument
    -0.62
     escaping
    -0.62
     incarcer
    -0.61
    container
    -0.61
     differentiation
    -0.61
    pmwiki
    -0.60
     evapor
    -0.59
    wcs
    -0.59
     membranes
    -0.59
    POSITIVE LOGITS
    amorph
    1.03
    ropolis
    0.97
    ropolitan
    0.88
    lehem
    0.86
    OTOS
    0.74
    yll
    0.73
    araoh
    0.73
    usalem
    0.73
    allic
    0.72
    aunt
    0.71
    Activations Density 0.029%

    No Known Activations