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. 5281
    Prev
    Next
    INDEX
    Explanations

    words related to considerations and factors in decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    various influential factors in decision-making processes

    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
    Arab
    -0.65
    arus
    -0.64
    little
    -0.63
    forts
    -0.63
    lang
    -0.63
    Else
    -0.63
    Fail
    -0.63
     starve
    -0.62
     Notes
    -0.62
    ipel
    -0.61
    POSITIVE LOGITS
     selecting
    1.22
     hiring
    1.15
     awarding
    1.14
     choosing
    1.11
     booking
    1.07
     determining
    1.07
     deciding
    1.07
     obtaining
    1.07
     accessing
    1.06
     purchasing
    1.06
    Activations Density 0.577%

    No Known Activations