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. 15217
    Prev
    Next
    INDEX
    Explanations

    words related to units of data size

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "ter"

    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
    ELS
    -0.77
    orship
    -0.75
    Downloadha
    -0.70
    UME
    -0.70
    issance
    -0.69
    OWS
    -0.66
    hetti
    -0.65
    éĹĺ
    -0.63
    etts
    -0.63
    ा
    -0.62
    POSITIVE LOGITS
    abytes
    1.18
    rible
    1.14
    rors
    1.09
    rier
    1.08
    ranean
    1.07
    riers
    1.05
    abyte
    1.04
    mination
    1.01
    mine
    1.01
    race
    1.00
    Activations Density 0.013%

    No Known Activations