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. 8-RES-JB
    6. 21977
    Prev
    Next
    INDEX
    Explanations

    instances where someone is unable to find something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of inability or obstacles in achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hate
    -0.68
     mourn
    -0.60
    monary
    -0.59
    hetamine
    -0.59
     derog
    -0.56
    orters
    -0.55
    imilation
    -0.54
    agate
    -0.53
    delete
    -0.53
     mourning
    -0.53
    POSITIVE LOGITS
     beforehand
    0.65
     deadline
    0.63
     deadlines
    0.60
     cheapest
    0.59
     Zup
    0.59
    PIN
    0.59
    zn
    0.58
     consultation
    0.58
     willing
    0.57
     Nicola
    0.57
    Activations Density 1.036%

    No Known Activations