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. 12862
    Prev
    Next
    INDEX
    Explanations

    phrases related to inspiration or motivation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to awareness and calls to action

    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
    rane
    -0.88
    dominated
    -0.84
    amas
    -0.83
    ague
    -0.81
    onde
    -0.80
    Invalid
    -0.78
    fed
    -0.78
    licensed
    -0.77
    bis
    -0.75
    ngth
    -0.74
    POSITIVE LOGITS
     message
    1.01
     mantra
    1.00
     tale
    0.99
     scenario
    0.99
     checklist
    0.98
     gesture
    0.94
     moment
    0.91
     ritual
    0.89
     button
    0.89
     vibe
    0.88
    Activations Density 0.237%

    No Known Activations