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. 7-RES-JB
    6. 772
    Prev
    Next
    INDEX
    Explanations

    the word "thing" that is followed by some additional context

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing what is critically important or essential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.75
    inav
    -0.73
    onz
    -0.73
    choes
    -0.70
    ilings
    -0.64
    DOM
    -0.63
    ped
    -0.63
    oufl
    -0.62
    brids
    -0.62
    undai
    -0.61
    POSITIVE LOGITS
     happened
    0.95
    iverse
    0.95
     happening
    0.91
     happens
    0.82
     transpired
    0.80
     missing
    0.76
     undone
    0.75
     bothering
    0.74
     happ
    0.74
     bothers
    0.69
    Activations Density 0.033%

    No Known Activations