© 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. 2-RES-JB
    11. 9426
    Prev
    Next
    INDEX
    Explanations

    the name "Paolo" at varying degrees of strong activation

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to Italian cuisine or culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writers
    -0.67
    present
    -0.66
    mark
    -0.66
    tags
    -0.65
    Condition
    -0.62
     hence
    -0.62
     ��������
    -0.62
     Conditions
    -0.62
    correct
    -0.59
    nah
    -0.59
    POSITIVE LOGITS
    olo
    1.46
    zzi
    1.11
    etooth
    1.07
    oaded
    0.96
    opsis
    0.95
    zzle
    0.95
    ogie
    0.92
    lette
    0.91
    Lens
    0.91
    zin
    0.91
    Activations Density 0.005%

    No Known Activations