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. 13094
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions or deals

    oai_token-act-pair · gpt-3.5-turbo

    elements associated with negative or derogatory descriptions

    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
    hedral
    -0.70
    oslav
    -0.67
    ĸļ
    -0.65
    MSN
    -0.65
    wake
    -0.62
    hu
    -0.62
    RAL
    -0.62
    iq
    -0.61
    ujah
    -0.61
     Ply
    -0.61
    POSITIVE LOGITS
    itely
    0.67
    eele
    0.63
    ħĭ
    0.62
    bender
    0.61
    iaries
    0.59
    BILITIES
    0.59
     Portug
    0.57
    ãĥīãĥ©
    0.57
    tein
    0.57
    upper
    0.56
    Activations Density 0.163%

    No Known Activations