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. 3-RES-JB
    6. 18847
    Prev
    Next
    INDEX
    Explanations

    phrases related to passing on responsibility or tradition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "torch" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilibrium
    -0.81
    akening
    -0.81
    oln
    -0.74
    alam
    -0.73
    nesota
    -0.73
    omal
    -0.71
    ele
    -0.70
    essor
    -0.68
    omes
    -0.67
    essors
    -0.65
    POSITIVE LOGITS
     torch
    1.04
    pole
    0.97
    light
    0.93
     torches
    0.93
     Torch
    0.88
    oshenko
    0.81
    beam
    0.80
     exting
    0.77
    itudinal
    0.77
    crow
    0.76
    Activations Density 0.007%

    No Known Activations