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

    Neuronpedia

    APICircuit 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. 16112
    Prev
    Next
    INDEX
    Explanations

    mentions of spiraling or escalating situations

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to spirals, particularly in a metaphorical or descriptive 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
    arers
    -0.79
    ropolitan
    -0.75
    prints
    -0.73
    oral
    -0.72
    arer
    -0.72
    ortment
    -0.71
    ynasty
    -0.70
    essee
    -0.69
     Played
    -0.69
    rica
    -0.68
    POSITIVE LOGITS
     spiral
    0.83
    iflower
    0.82
     staircase
    0.81
    OUS
    0.81
    vier
    0.80
     spir
    0.79
    ITY
    0.78
    iously
    0.76
    aceous
    0.75
    iculture
    0.74
    Activations Density 0.090%

    No Known Activations