Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7588
    Prev
    Next
    INDEX
    Explanations

    instances of missing or being unable to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "miss" and its variations

    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
    pour
    -0.71
    loo
    -0.70
     Jinping
    -0.69
    Reviewer
    -0.65
    escal
    -0.65
    btn
    -0.64
    bis
    -0.63
    levels
    -0.62
    Kar
    -0.61
     pos
    -0.61
    POSITIVE LOGITS
    pelled
    1.21
    hap
    1.02
    pelling
    0.99
    poke
    0.98
    pell
    0.94
    peak
    0.88
    ouri
    0.86
     curfew
    0.86
     deadlines
    0.81
    ordable
    0.71
    Activations Density 0.025%

    No Known Activations