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. 17700
    Prev
    Next
    INDEX
    Explanations

    strong verbs or nouns ending in '-ing'

    oai_token-act-pair · gpt-3.5-turbo

    words that suggest strength or robustness

    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
     drum
    -0.72
     stink
    -0.71
    spin
    -0.70
     dust
    -0.69
     fever
    -0.68
     rift
    -0.67
     fuss
    -0.66
     sweat
    -0.65
     spin
    -0.64
     trump
    -0.63
    POSITIVE LOGITS
    itionally
    1.06
    ations
    1.06
    ivably
    1.04
    ational
    1.01
    atic
    0.99
    itably
    0.98
    ATIONS
    0.96
    ances
    0.96
    atically
    0.93
    aci
    0.93
    Activations Density 0.155%

    No Known Activations