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. 9-RES-JB
    6. 172
    Prev
    Next
    INDEX
    Explanations

    references to specific ages or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to age and time-related details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entirety
    -0.70
     polygamy
    -0.69
     misogyny
    -0.66
     VIDEOS
    -0.65
     Lifetime
    -0.65
     specialization
    -0.63
     absurdity
    -0.63
     caveats
    -0.61
     patents
    -0.61
     limitation
    -0.60
    POSITIVE LOGITS
     asleep
    0.93
     distraught
    0.91
     stunned
    0.91
     horrified
    0.86
     acquitted
    0.86
     shocked
    0.86
     relieved
    0.85
     estranged
    0.84
     shy
    0.83
     reluctant
    0.82
    Activations Density 0.358%

    No Known Activations