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. 15442
    Prev
    Next
    INDEX
    Explanations

    words that are interspersed or interleaved within a sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "sp" within words

    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
    ãĥĥãĥĪ
    -0.79
    ĪĴ
    -0.78
    âĸ¬âĸ¬
    -0.73
     behold
    -0.71
    sbm
    -0.71
    WAYS
    -0.67
    vironment
    -0.66
    hof
    -0.65
     Brotherhood
    -0.64
    naissance
    -0.64
    POSITIVE LOGITS
    atial
    1.13
    iral
    1.09
    iegel
    1.05
    aghetti
    1.04
    acious
    1.04
    encer
    1.02
    acer
    1.00
    onge
    0.99
    ending
    0.97
    ooky
    0.95
    Activations Density 0.020%

    No Known Activations