© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1714
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    the symbol that represents a bullet point or marker in lists

    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
     board
    -0.69
     Unified
    -0.61
     NEC
    -0.59
     Voyager
    -0.59
     managerial
    -0.59
     inform
    -0.58
     unmarked
    -0.57
     Cambod
    -0.56
     director
    -0.56
     Conservative
    -0.56
    POSITIVE LOGITS
    ¬
    1.39
    ¡
    1.33
    ı
    1.30
    Ĵ
    1.28
    ¤
    1.26
    Ļ
    1.24
    ľ
    1.21
    §
    1.18
    µ
    1.17
    £
    1.17
    Activations Density 0.417%

    No Known Activations