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. 20557
    Prev
    Next
    INDEX
    Explanations

    abbreviations or terms related to technology or medical fields

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SP" in various contexts

    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
    taboola
    -0.79
    ãĥĥãĥĪ
    -0.73
    sbm
    -0.73
     behold
    -0.70
    hower
    -0.70
    omorph
    -0.69
    ogen
    -0.67
     subord
    -0.67
    omorphic
    -0.66
    ographed
    -0.65
    POSITIVE LOGITS
    EED
    1.37
    ORT
    1.16
    ORTS
    1.16
    OIL
    1.14
    ONSORED
    1.07
    IR
    0.99
    HER
    0.96
    ECT
    0.96
    ENCE
    0.94
    OOL
    0.94
    Activations Density 0.013%

    No Known Activations