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. 12-RES-JB
    6. 14711
    Prev
    Next
    INDEX
    Explanations

    references to specific events or people related to legal and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to identities and their significance in the context of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Shutterstock
    -0.77
    itia
    -0.72
    vertisement
    -0.69
    tackle
    -0.68
    gyn
    -0.67
    erb
    -0.66
    arming
    -0.66
    book
    -0.66
    vice
    -0.65
    Bey
    -0.65
    POSITIVE LOGITS
     identities
    1.52
     whereabouts
    1.51
     identity
    1.46
     extent
    1.40
     origins
    1.37
     origin
    1.30
     precise
    1.26
     exact
    1.26
     true
    1.22
     motives
    1.20
    Activations Density 0.272%

    No Known Activations