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. 9-RES-JB
    6. 22273
    Prev
    Next
    INDEX
    Explanations

    words related to requests, requirements, and rescues

    oai_token-act-pair · gpt-3.5-turbo

    words related to requests and rescue operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dash
    -0.70
     HIP
    -0.69
    DOM
    -0.67
     miscarriage
    -0.66
     Nicotine
    -0.66
     genders
    -0.63
     twist
    -0.63
     Franch
    -0.63
     contrace
    -0.61
    words
    -0.61
    POSITIVE LOGITS
    isition
    1.22
    isitions
    1.18
    ests
    1.18
    irement
    1.18
    uers
    1.14
    ited
    1.11
    ues
    1.11
    irements
    1.09
    uez
    1.05
    iencies
    1.05
    Activations Density 0.065%

    No Known Activations