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. 22156
    Prev
    Next
    INDEX
    Explanations

    instances where the text describes a specific event or situation in detail

    oai_token-act-pair · gpt-3.5-turbo

    references to time and place in a narrative context

    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
    vantage
    -0.79
    anon
    -0.69
    ombat
    -0.69
    elly
    -0.68
    .:
    -0.65
    .(
    -0.64
    :#
    -0.64
    apest
    -0.63
    ogether
    -0.62
    :(
    -0.62
    POSITIVE LOGITS
     consultation
    0.67
    accompanied
    0.61
     waning
    0.60
     Improvement
    0.59
    otiation
    0.58
     reviewing
    0.58
     announcing
    0.58
     holidays
    0.54
     commem
    0.54
    lication
    0.54
    Activations Density 0.309%

    No Known Activations