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. 7152
    Prev
    Next
    INDEX
    Explanations

    dates specified in a particular format (for example, "June 20" expressed as "six/20")

    oai_token-act-pair · gpt-3.5-turbo

    specific dates related to events

    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
    orable
    -0.73
    ensed
    -0.63
    rw
    -0.63
    attled
    -0.62
    akespe
    -0.61
    wx
    -0.60
     scissors
    -0.59
    edIn
    -0.58
     loves
    -0.57
     hygiene
    -0.56
    POSITIVE LOGITS
    th
    1.30
    ths
    0.89
    TH
    0.88
    rd
    0.85
    teenth
    0.82
     Forth
    0.73
    âĸĪâĸĪ
    0.70
     onwards
    0.68
    eteenth
    0.65
    2200
    0.65
    Activations Density 0.089%

    No Known Activations