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. 4773
    Prev
    Next
    INDEX
    Explanations

    mention of specific locations or facilities related to daily activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific objects, actions, and concepts associated with daily life and societal responsibilities

    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
    hap
    -0.48
    actionDate
    -0.46
     SPI
    -0.45
     Amb
    -0.45
     Tony
    -0.44
    oba
    -0.44
    ived
    -0.43
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.43
    NBC
    -0.42
     Adren
    -0.42
    POSITIVE LOGITS
    ahime
    0.63
     destro
    0.60
     rul
    0.59
    utenberg
    0.54
    chuk
    0.53
     nodd
    0.53
     shenan
    0.52
    queue
    0.51
    rique
    0.50
    ij士
    0.50
    Activations Density 1.390%

    No Known Activations