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. 5411
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "essential."

    oai_token-act-pair · gpt-3.5-turbo

    usage of the word "essential" and its variations in different contexts

    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
    Roy
    -0.82
    creen
    -0.75
    hare
    -0.74
    renheit
    -0.71
    kers
    -0.68
    OUT
    -0.68
    elled
    -0.67
    adra
    -0.67
     Nights
    -0.66
    shirt
    -0.66
    POSITIVE LOGITS
     ingredient
    0.93
     essential
    0.91
    essential
    0.87
     prerequisite
    0.84
     components
    0.83
     ingred
    0.81
     essentials
    0.79
    iary
    0.78
    isin
    0.78
     prec
    0.77
    Activations Density 0.019%

    No Known Activations