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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5841
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistics and concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to concepts or terms indicative of societal or political issues

    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
     calculations
    -0.65
     dismantling
    -0.63
     adaptations
    -0.62
     scraps
    -0.62
     experiments
    -0.61
     routines
    -0.59
     recordings
    -0.58
     traject
    -0.58
     nightly
    -0.58
     collaborations
    -0.57
    POSITIVE LOGITS
    âĢİ
    0.86
     signifies
    0.79
     refers
    0.74
     denotes
    0.73
     implies
    0.71
    -.
    0.69
    orah
    0.68
    _.
    0.68
     denote
    0.67
    Accessory
    0.67
    Activations Density 0.369%

    No Known Activations