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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 21275
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal structures and frameworks

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal structures and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificantly
    -0.80
    isoft
    -0.70
    registered
    -0.68
    orthy
    -0.68
    ificant
    -0.66
    inion
    -0.64
    regulated
    -0.64
    olute
    -0.63
    Sensor
    -0.61
    vel
    -0.60
    POSITIVE LOGITS
     confines
    0.89
     afforded
    0.86
    antry
    0.73
     mund
    0.70
     portrayed
    0.69
    ounters
    0.68
    stones
    0.68
     nature
    0.67
     surrounding
    0.67
    behind
    0.66
    Activations Density 0.683%

    No Known Activations