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. 8-RES-JB
    6. 4404
    Prev
    Next
    INDEX
    Explanations

    words related to Catalonia and phrases associated with cathartic experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to Catalonia and related socio-political 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
    ly
    -0.88
     sleeper
    -0.72
    notes
    -0.63
    instein
    -0.59
    ó
    -0.58
    manship
    -0.58
    netflix
    -0.58
    busters
    -0.58
     marginal
    -0.58
     Predator
    -0.58
    POSITIVE LOGITS
    ocrat
    1.00
    ars
    0.92
    mination
    0.90
    arist
    0.87
    imer
    0.84
    inarily
    0.83
    inez
    0.80
    aterial
    0.80
    ocratic
    0.79
    odes
    0.76
    Activations Density 0.129%

    No Known Activations