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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 188
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and recognition towards others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disrupting
    -0.71
    scape
    -0.67
     prototypes
    -0.67
     nightmares
    -0.66
     disrupted
    -0.64
     photographed
    -0.63
     headlines
    -0.63
     indoors
    -0.63
     disruptive
    -0.63
     overnight
    -0.62
    POSITIVE LOGITS
     bestowed
    0.81
    udos
    0.75
    nat
    0.73
    entin
    0.72
    enza
    0.71
    edi
    0.71
    llah
    0.69
    ends
    0.67
     Cosponsors
    0.67
     Towards
    0.67
    Activations Density 0.245%

    No Known Activations