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. 17541
    Prev
    Next
    INDEX
    Explanations

    words related to military ranks and positions

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to military and authority figures

    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
    ilion
    -0.76
    fman
    -0.71
    oho
    -0.69
    etting
    -0.68
     bloom
    -0.66
    undai
    -0.65
    iggurat
    -0.64
    esting
    -0.64
    ether
    -0.64
    anwhile
    -0.64
    POSITIVE LOGITS
     extraord
    1.38
    esses
    1.15
    hood
    1.03
    ial
    0.99
     Beware
    0.98
    ess
    0.94
    stown
    0.90
    NAME
    0.89
     Candidate
    0.88
     beware
    0.86
    Activations Density 0.250%

    No Known Activations