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. 4-RES-JB
    6. 23321
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of "outright" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outright" used in various contexts

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

    No Comments

    Negative Logits
    agine
    -0.80
    anwhile
    -0.75
    arts
    -0.74
    nan
    -0.74
    anners
    -0.73
    ulton
    -0.72
    yer
    -0.70
    odan
    -0.70
    nesota
    -0.68
    ramid
    -0.66
    POSITIVE LOGITS
    eless
    0.80
    ãĤ¦ãĤ¹
    0.74
    Discuss
    0.74
     hostility
    0.71
     guiActiveUn
    0.71
    Introduced
    0.69
    shown
    0.67
     rewriting
    0.67
    ãĥij
    0.64
    ãĥ
    0.64
    Activations Density 0.006%

    No Known Activations