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. 7-RES-JB
    6. 15181
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about urban environments and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to critique and exposure of societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finder
    -0.76
     Edison
    -0.75
     Compass
    -0.75
    venants
    -0.73
     appreciated
    -0.73
    foreseen
    -0.71
     Fres
    -0.69
    accompan
    -0.66
    rect
    -0.65
    REE
    -0.64
    POSITIVE LOGITS
     pretend
    1.18
     shameless
    1.17
     excuses
    1.14
     phony
    1.13
     obfusc
    1.12
     fools
    1.11
     bullshit
    1.09
     excuse
    1.09
     pretending
    1.08
     hypocrisy
    1.07
    Activations Density 1.800%

    No Known Activations