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. 8-RES-JB
    6. 4398
    Prev
    Next
    INDEX
    Explanations

    sentences related to issues of personal freedom and rights

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to coercion or force in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.67
     bullish
    -0.64
    iatus
    -0.63
     ORIG
    -0.62
    iHUD
    -0.61
    OUT
    -0.61
     FANT
    -0.60
     hyp
    -0.60
     teaser
    -0.59
     IMAGES
    -0.59
    POSITIVE LOGITS
     shouldn
    0.87
     shalt
    0.85
     prohibit
    0.83
    ctors
    0.82
     ought
    0.81
     permissible
    0.81
    untary
    0.80
     forbid
    0.80
     compulsion
    0.80
     prohibits
    0.76
    Activations Density 0.618%

    No Known Activations