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. 347
    Prev
    Next
    INDEX
    Explanations

    expressions related to loss and regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of loss and permanence

    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
    ses
    -0.66
    ahime
    -0.65
    MpServer
    -0.64
    ij士
    -0.64
    soType
    -0.63
     largeDownload
    -0.61
    Newsletter
    -0.59
    iHUD
    -0.58
    edIn
    -0.58
    externalActionCode
    -0.58
    POSITIVE LOGITS
    theless
    1.29
     again
    1.01
    again
    0.98
     EVER
    0.98
     forgive
    0.96
     underestimate
    0.91
     admit
    0.88
     regain
    0.86
     cease
    0.84
     forget
    0.84
    Activations Density 0.041%

    No Known Activations