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. 9959
    Prev
    Next
    INDEX
    Explanations

    references to specific groups of people or communities within a geographical area

    oai_token-act-pair · gpt-3.5-turbo

    references to community groups and their interactions

    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
    zac
    -0.70
     Camer
    -0.70
    acco
    -0.69
    upt
    -0.68
     Mortgage
    -0.68
    otom
    -0.67
     Loans
    -0.65
     Chocolate
    -0.64
    Course
    -0.62
    antly
    -0.62
    POSITIVE LOGITS
    tale
    0.85
    lore
    0.82
    LECT
    0.80
    oji
    0.79
    ords
    0.76
    hari
    0.74
    erest
    0.71
    roots
    0.68
    è£
    0.67
    icial
    0.66
    Activations Density 0.061%

    No Known Activations