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. 6-RES-JB
    6. 19005
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to potentially traumatic experiences or serious incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.80
    âĦ¢:
    -0.69
    oliberal
    -0.66
     domestically
    -0.64
     premier
    -0.63
    osphere
    -0.62
     Throne
    -0.60
     billionaires
    -0.60
     asteroid
    -0.60
     antitrust
    -0.60
    POSITIVE LOGITS
    Eventually
    0.88
    upon
    0.84
    Later
    0.84
    Suddenly
    0.76
    Then
    0.75
     luckily
    0.74
    gered
    0.71
    then
    0.70
     calmed
    0.69
    sequently
    0.69
    Activations Density 1.229%

    No Known Activations