© 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. 10-RES-JB
    11. 9939
    Prev
    Next
    INDEX
    Explanations

    explanations or reasons for assertions

    oai_token-act-pair · gpt-3.5-turbo

    negative qualifiers and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.74
    isSpecialOrderable
    -0.72
    ç«
    -0.71
    ARM
    -0.67
     Hots
    -0.66
    çļ
    -0.66
    çīĪ
    -0.65
    SourceFile
    -0.64
     Consortium
    -0.64
    20439
    -0.64
    POSITIVE LOGITS
     necessarily
    1.44
     inherently
    1.27
     infall
    1.21
     always
    1.15
     magically
    1.06
     immune
    1.01
     intrinsically
    1.00
    always
    0.97
     automatically
    0.94
     ALWAYS
    0.92
    Activations Density 0.216%

    No Known Activations