© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11602
    Prev
    Next
    INDEX
    Explanations

    names or words that end with 'z'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HMS
    -0.66
     futures
    -0.65
     disqualified
    -0.61
     foreground
    -0.61
     behalf
    -0.58
     susp
    -0.57
     Norwegian
    -0.57
     gener
    -0.57
     Peru
    -0.56
     contrary
    -0.56
    POSITIVE LOGITS
    z
    3.90
    zl
    2.34
    zes
    2.17
    zman
    2.04
    Z
    2.01
    zer
    2.00
    zie
    2.00
    zy
    1.97
    zn
    1.97
    zel
    1.96
    Activations Density 0.028%

    No Known Activations