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. 0-RES-JB
    6. 21117
    Prev
    Next
    INDEX
    Explanations

    words related to negative connotations or actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "disservice" or situations where service is inadequate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polo
    -0.82
    peak
    -0.75
    pire
    -0.72
    peed
    -0.70
    luck
    -0.69
     GMT
    -0.69
     Sochi
    -0.69
    gold
    -0.67
    PB
    -0.67
    wine
    -0.66
    POSITIVE LOGITS
     dis
    3.26
     Dis
    1.59
    dis
    1.54
    Dis
    1.47
     disl
    1.46
     demoral
    1.41
     disse
    1.41
     disarm
    1.40
     DIS
    1.35
     dism
    1.32
    Activations Density 0.023%

    No Known Activations