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. 16774
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or experiences

    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
     tomorrow
    -0.86
     tonight
    -0.78
     Continuing
    -0.73
    morrow
    -0.70
    wake
    -0.69
     Yesterday
    -0.66
     contemporary
    -0.65
    today
    -0.64
    oday
    -0.62
     extension
    -0.61
    POSITIVE LOGITS
     relied
    1.10
     tended
    1.06
     consisted
    1.00
     seemed
    0.99
     hadn
    0.98
     assumed
    0.98
     feared
    0.95
     thought
    0.94
     existed
    0.93
     hesitated
    0.92
    Activations Density 0.270%

    No Known Activations