© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20438
    Prev
    Next
    INDEX
    Explanations

    the word "za" with different connotations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Adrian."

    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
     screen
    -0.71
     Ack
    -0.63
     pots
    -0.62
     NR
    -0.59
     screens
    -0.59
     unused
    -0.58
     ref
    -0.58
     monitor
    -0.58
     inadequ
    -0.57
     filings
    -0.56
    POSITIVE LOGITS
    za
    4.68
    ZA
    1.91
    zza
    1.78
    zo
    1.71
    zan
    1.59
    ze
    1.54
    zi
    1.51
    zos
    1.47
    zai
    1.44
    ja
    1.40
    Activations Density 0.019%

    No Known Activations