© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    special characters indicating an action or thought

    oai_token-act-pair · gpt-3.5-turbo

    variations of a particular character or typographical error in text

    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
     scatter
    -0.71
     coast
    -0.67
     guiActiveUnfocused
    -0.65
     scattering
    -0.63
     minim
    -0.62
     relocation
    -0.62
     treadmill
    -0.61
     farm
    -0.61
     cyan
    -0.61
     target
    -0.61
    POSITIVE LOGITS
    âĹ¼
    1.00
    ¢
    0.97
    âĢķ
    0.96
    £
    0.95
    âĢ
    0.91
    âģ
    0.90
    âĢł
    0.90
    ¯
    0.89
    ¹
    0.88
    say
    0.86
    Activations Density 0.838%

    No Known Activations