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. 12116
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movements or actions, such as flailing around, writhing in pain, or bending over backwards

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating movement or location

    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
    listed
    -0.74
    querque
    -0.69
    trip
    -0.67
    soDeliveryDate
    -0.65
    vP
    -0.65
    alty
    -0.65
    saf
    -0.64
     Poll
    -0.64
    EMENT
    -0.63
    peria
    -0.61
    POSITIVE LOGITS
     seams
    0.99
    wards
    0.88
     corners
    0.86
     uncontroll
    0.79
     obscurity
    0.74
     hither
    0.71
    ön
    0.70
     unpredict
    0.69
     edges
    0.68
     bushes
    0.67
    Activations Density 0.301%

    No Known Activations