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. 2320
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone being taken to a medical facility or custody

    oai_token-act-pair · gpt-3.5-turbo

    instances of being taken to places, particularly hospitals or custody-related contexts

    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
    natureconservancy
    -0.88
     overlap
    -0.77
     ingenuity
    -0.68
     indu
    -0.67
     @@
    -0.64
     seq
    -0.63
     derived
    -0.61
     gob
    -0.61
     appet
    -0.61
     sear
    -0.60
    POSITIVE LOGITS
    oult
    0.88
    oat
    0.78
    olt
    0.77
    odan
    0.73
    uper
    0.73
    ravel
    0.73
    ospital
    0.73
    ADRA
    0.72
     Detention
    0.72
    osure
    0.69
    Activations Density 0.235%

    No Known Activations