© 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. 7-RES-JB
    11. 3867
    Prev
    Next
    INDEX
    Explanations

    blank spaces or absences in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical values embedded in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.83
    wagen
    -0.72
     destro
    -0.71
     delegation
    -0.70
     Asheville
    -0.68
     disproportion
    -0.68
     Mellon
    -0.67
     braces
    -0.67
     potatoes
    -0.66
     succeeding
    -0.65
    POSITIVE LOGITS
    ________________________________________________________________
    1.03
    iced
    1.01
    Ë
    0.98
    xt
    0.97
    Ñģ
    0.96
    Ëľ
    0.94
    ********
    0.94
    iph
    0.94
    ________
    0.93
    à¸
    0.92
    Activations Density 0.012%

    No Known Activations