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. 7-RES-JB
    6. 24349
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations or actions involving force or conflict

    oai_token-act-pair · gpt-3.5-turbo

    patterns or sequences related to physical objects or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.86
    Services
    -0.76
    SHARE
    -0.76
    general
    -0.74
    DATA
    -0.72
    MENT
    -0.71
    Daily
    -0.70
    BLIC
    -0.69
    SEA
    -0.69
    è£ħ
    -0.69
    POSITIVE LOGITS
    opping
    0.76
    alog
    0.76
    oche
    0.75
    usters
    0.71
    otted
    0.71
    iley
    0.70
     heels
    0.70
    ooth
    0.70
     whisk
    0.68
    ippers
    0.68
    Activations Density 0.135%

    No Known Activations