© 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. 11-RES-JB
    11. 9974
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding methods and functions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving methods and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iann
    -0.73
     acknowled
    -0.70
     outl
    -0.66
     proud
    -0.61
     expectations
    -0.61
     belonged
    -0.60
    ivities
    -0.60
    gements
    -0.59
    BuyableInstoreAndOnline
    -0.59
     scrutiny
    -0.58
    POSITIVE LOGITS
    Alternatively
    1.00
    Solution
    0.98
    Option
    0.92
    Alternative
    0.91
    method
    0.90
     workaround
    0.89
     Altern
    0.89
     alternative
    0.88
     Alternative
    0.87
     Option
    0.85
    Activations Density 0.627%

    No Known Activations