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. 6480
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preferences or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    elements that represent children's entertainment or interests

    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
     Presidency
    -0.79
    jri
    -0.70
     unification
    -0.68
     behavi
    -0.67
     recovery
    -0.63
     Priebus
    -0.63
     perspect
    -0.61
    Fine
    -0.61
     Frey
    -0.60
     stabilization
    -0.58
    POSITIVE LOGITS
     dread
    0.88
     aspire
    0.85
     crave
    0.84
     coveted
    0.83
     frequ
    0.81
     cherish
    0.80
     envy
    0.80
     admired
    0.79
     sorely
    0.76
    miss
    0.76
    Activations Density 0.221%

    No Known Activations