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. 5-RES-JB
    6. 19405
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something happening continuously or consistently throughout a period of time

    oai_token-act-pair · gpt-3.5-turbo

    the word "throughout."

    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
    potion
    -0.74
    elling
    -0.71
    rets
    -0.71
    JV
    -0.69
    LS
    -0.68
    bol
    -0.68
    INS
    -0.66
    hl
    -0.66
    umo
    -0.65
    GE
    -0.65
    POSITIVE LOGITS
    eatures
    0.79
     disciplines
    0.77
     stages
    0.77
    vironment
    0.73
     Europe
    0.71
    ciating
    0.70
     phases
    0.69
     XD
    0.69
     Wage
    0.69
    ĸļ
    0.67
    Activations Density 0.018%

    No Known Activations