Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 556
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to detention facilities or centers

    oai_token-act-pair · gpt-3.5-turbo

    references to detention facilities and the conditions surrounding them

    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
    chrom
    -0.68
    clerosis
    -0.66
    ãĥ£
    -0.64
    bold
    -0.64
    Roll
    -0.63
    soDeliveryDate
    -0.63
    hl
    -0.62
    ocaly
    -0.61
    raviolet
    -0.61
    odic
    -0.61
    POSITIVE LOGITS
     detention
    0.97
    rooms
    0.85
     detainees
    0.85
     detain
    0.84
     detained
    0.81
    anamo
    0.79
     facilities
    0.76
    ainers
    0.76
    rans
    0.74
     Facility
    0.72
    Activations Density 0.023%

    No Known Activations