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. 14345
    Prev
    Next
    INDEX
    Explanations

    phrases that describe the time or effort required to accomplish a task

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the concept of effort and the time required to achieve something

    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
    tions
    -0.70
     rebell
    -0.66
    holm
    -0.66
    tor
    -0.66
    nesses
    -0.65
    entric
    -0.63
     Patron
    -0.63
    dor
    -0.62
    raid
    -0.62
    eers
    -0.61
    POSITIVE LOGITS
    aways
    0.94
     aback
    0.90
    YR
    0.82
     advantage
    0.81
    overs
    0.80
    FINE
    0.75
    ioxide
    0.75
    reads
    0.75
    OVER
    0.74
     care
    0.72
    Activations Density 0.088%

    No Known Activations