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. 11535
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical data expressed in rates and frequencies

    oai_token-act-pair · gpt-3.5-turbo

    quantities and numerical data related to frequency or ratios

    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
    rawdownloadcloneembedreportprint
    -0.80
    eele
    -0.75
    trak
    -0.68
    usky
    -0.65
     laure
    -0.63
    oki
    -0.61
    retty
    -0.61
    itech
    -0.60
    helm
    -0.60
    oren
    -0.60
    POSITIVE LOGITS
    ãĤ°
    0.75
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    ãĥŁ
    0.70
    million
    0.66
     ns
    0.65
    lishes
    0.65
     Billion
    0.65
    billion
    0.64
     increment
    0.64
     square
    0.64
    Activations Density 0.081%

    No Known Activations