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. 10-RES-JB
    6. 2159
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or evaluating something negatively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'r'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sons
    -0.74
     cardio
    -0.66
     hers
    -0.64
     EntityItem
    -0.64
     ROM
    -0.64
     Lobby
    -0.60
     mine
    -0.60
     ours
    -0.60
     rope
    -0.59
     SOS
    -0.58
    POSITIVE LOGITS
    ipples
    1.39
    ambling
    1.33
    ifling
    1.33
    umbling
    1.28
    agged
    1.27
    iddle
    1.27
    attle
    1.26
    iddles
    1.26
    haps
    1.23
    angers
    1.23
    Activations Density 0.015%

    No Known Activations