Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1731
    Prev
    Next
    INDEX
    Explanations

    terms related to specific objects or subjects, such as "squats," "DGX," "Motorola," and "fingerprint checks."

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical actions and conditions

    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
     lately
    -0.79
     Recently
    -0.69
     recent
    -0.67
     Earlier
    -0.65
     unlike
    -0.59
    Recently
    -0.59
    acio
    -0.58
    tained
    -0.58
     Yesterday
    -0.57
     recently
    -0.57
    POSITIVE LOGITS
     will
    1.41
     becomes
    1.33
     would
    1.29
     ceases
    1.23
     might
    1.19
     could
    1.17
     should
    1.16
     must
    1.16
    will
    1.15
     may
    1.14
    Activations Density 0.453%

    No Known Activations