Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12806
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "against"

    oai_token-act-pair · gpt-3.5-turbo

    cautionary statements or warnings

    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
    arity
    -0.78
    iseum
    -0.77
    onductor
    -0.74
    undred
    -0.73
    arta
    -0.71
    minus
    -0.69
    nine
    -0.68
    hai
    -0.67
    ought
    -0.67
    orld
    -0.66
    POSITIVE LOGITS
     adopting
    1.00
     commenting
    0.97
     recommending
    0.96
     trusting
    0.94
     underest
    0.91
     divul
    0.89
     pursuing
    0.88
     discussing
    0.87
     accepting
    0.87
     interpreting
    0.85
    Activations Density 0.174%

    No Known Activations