© 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. 18234
    Prev
    Next
    INDEX
    Explanations

    terms related to linguistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic disciplines or fields of study

    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
    ardless
    -0.85
    loaded
    -0.70
    ãģĤ
    -0.69
    fired
    -0.67
     shred
    -0.65
    holders
    -0.64
     recall
    -0.64
    packed
    -0.63
    shall
    -0.63
     curtains
    -0.63
    POSITIVE LOGITS
     Warfare
    0.98
    uca
    0.83
    mith
    0.82
    gorithm
    0.82
     Sciences
    0.81
     Advice
    0.80
    gebra
    0.79
     Compass
    0.78
    alysis
    0.78
    ãĤ¶
    0.78
    Activations Density 0.101%

    No Known Activations