© 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. 4495
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns

    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
    ãĤ©
    -0.61
    ntil
    -0.56
    ÑĤ
    -0.56
    ACTION
    -0.54
    -+-+
    -0.52
    ļé
    -0.52
     conflic
    -0.52
    %"
    -0.52
    ¿½
    -0.52
    ¿
    -0.51
    POSITIVE LOGITS
    sburg
    0.62
    pedia
    0.61
    iac
    0.55
     Heights
    0.53
    shire
    0.53
    puff
    0.53
     IMAGES
    0.50
     Lodge
    0.50
    gur
    0.50
    dale
    0.49
    Activations Density 0.823%

    No Known Activations