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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5855
    Prev
    Next
    INDEX
    Explanations

    instances of a specific time duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or specific timeframes for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.70
     promot
    -0.69
     tolerated
    -0.66
    heed
    -0.64
     brakes
    -0.63
    orest
    -0.63
    ourge
    -0.62
     intimately
    -0.62
     insulted
    -0.61
     existed
    -0.61
    POSITIVE LOGITS
     nutshell
    1.09
     case
    0.82
     context
    0.80
     meantime
    0.79
     guise
    0.76
     cases
    0.75
     mode
    0.73
    ç¥ŀ
    0.73
     vein
    0.67
    lance
    0.67
    Activations Density 0.287%

    No Known Activations