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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4-RES-JB
    6. 3891
    Prev
    Next
    INDEX
    Explanations

    superlatives indicating the best or the most

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and phrases related to prominence or effectiveness

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

    No Comments

    Negative Logits
     Indra
    -0.66
    pas
    -0.63
    raine
    -0.61
    zek
    -0.60
     Mahm
    -0.59
    anism
    -0.58
    clusions
    -0.58
    ipt
    -0.57
    hots
    -0.57
     Seym
    -0.57
    POSITIVE LOGITS
    hest
    0.91
     practicable
    0.86
     possible
    0.81
    liest
    0.79
     bidder
    0.75
    est
    0.74
     conceivable
    0.74
     allowable
    0.73
     bang
    0.72
     amount
    0.72
    Activations Density 0.195%

    No Known Activations