© 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. 811
    Prev
    Next
    INDEX
    Explanations

    the word "Common" when it is part of a title or a specific term

    oai_token-act-pair · gpt-4-turbo

    references to the term "Common"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Common" related topics or standards

    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
    ackers
    -0.73
     Janeiro
    -0.69
    olulu
    -0.68
    udging
    -0.67
    industrial
    -0.66
    Ń·
    -0.65
    choes
    -0.65
    cients
    -0.65
    okin
    -0.64
    otos
    -0.63
    POSITIVE LOGITS
    wealth
    1.01
     Common
    0.97
    Parameters
    0.96
    ensical
    0.90
     Lisp
    0.80
    Common
    0.76
    Sense
    0.73
    enough
    0.70
    alities
    0.70
    nces
    0.68
    Activations Density 0.007%

    No Known Activations