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. 13212
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting or contradictory statements

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or expressions of agreement

    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
    ]:
    -0.79
    lier
    -0.76
    ESE
    -0.72
    interstitial
    -0.71
    uten
    -0.69
    Connector
    -0.69
    backer
    -0.69
    ]).
    -0.68
    opsis
    -0.68
    ipel
    -0.68
    POSITIVE LOGITS
     admittedly
    0.98
     technically
    0.95
     disagree
    0.89
     inconvenience
    0.79
     but
    0.77
     imperfect
    0.76
     superf
    0.75
     laud
    0.74
     initially
    0.73
     merits
    0.71
    Activations Density 0.607%

    No Known Activations