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. 11-RES-JB
    6. 4320
    Prev
    Next
    INDEX
    Explanations

    mentions of human figures and their interactions in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    names and roles of individuals involved in an incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fulfillment
    -0.69
     advertis
    -0.69
    Quantity
    -0.66
    hibition
    -0.66
     fulfil
    -0.65
    btn
    -0.65
    hibit
    -0.63
    tumblr
    -0.63
    problem
    -0.62
    funding
    -0.61
    POSITIVE LOGITS
     alerted
    1.18
     yelled
    1.14
     rushed
    1.13
     witnessed
    1.12
     chased
    1.11
     evacuated
    1.07
     ejected
    1.06
     awoke
    1.03
     heard
    1.03
     spotted
    1.01
    Activations Density 0.263%

    No Known Activations