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. 10-RES-JB
    6. 18428
    Prev
    Next
    INDEX
    Explanations

    verbs related to making decisions or taking actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the need to take action or make decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescence
    -0.84
    ankind
    -0.67
    luaj
    -0.64
    oulos
    -0.64
    erno
    -0.62
    nih
    -0.62
     purported
    -0.61
    ensable
    -0.61
    owler
    -0.60
    riched
    -0.60
    POSITIVE LOGITS
     somewhere
    1.00
     manually
    0.97
     lest
    0.87
     harder
    0.79
    dress
    0.78
     somew
    0.76
     something
    0.76
     urgently
    0.76
     compromises
    0.75
     tougher
    0.75
    Activations Density 0.281%

    No Known Activations