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. 6-RES-JB
    6. 2319
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names of people or places, particularly focusing on the name "Bram."

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with places and intense emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Situation
    -0.74
    selection
    -0.70
     DISTR
    -0.68
     Malays
    -0.65
     Malaysian
    -0.62
    lace
    -0.61
     PRESS
    -0.60
    uthor
    -0.59
    lift
    -0.59
     TRAN
    -0.59
    POSITIVE LOGITS
    pton
    1.08
    ados
    0.92
    uits
    0.92
    atile
    0.91
    ents
    0.91
    etooth
    0.90
    ancies
    0.86
    acco
    0.86
    ibel
    0.83
    nant
    0.83
    Activations Density 0.041%

    No Known Activations