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. 14612
    Prev
    Next
    INDEX
    Explanations

    information related to medical procedures and conditions during various stages of pregnancy

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to gestational periods and medical terminology related to abortions

    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
     pounds
    -0.33
     weddings
    -0.30
     razor
    -0.30
     unwanted
    -0.29
     manic
    -0.29
     pige
    -0.28
     prank
    -0.28
    20439
    -0.28
     wedding
    -0.28
     chores
    -0.27
    POSITIVE LOGITS
    ]."
    0.44
    )."
    0.43
    }.
    0.43
    éļ
    0.42
    ;;;;;;;;;;;;
    0.41
    anwhile
    0.40
    govtrack
    0.39
    ]).
    0.39
    arta
    0.39
     Antar
    0.38
    Activations Density 3.619%

    No Known Activations