© 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
    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. 22088
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or extreme behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intention and environmental factors

    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
    TER
    -0.64
     Berk
    -0.57
    mosp
    -0.55
    wine
    -0.53
    worth
    -0.52
    âĺħâĺħ
    -0.51
     disinfect
    -0.51
    cu
    -0.51
    iage
    -0.50
    STEM
    -0.50
    POSITIVE LOGITS
    al
    2.76
    als
    2.46
    alist
    2.37
    ally
    2.16
    ality
    2.05
    AL
    1.97
    aled
    1.86
    alities
    1.85
    ALS
    1.78
    aler
    1.73
    Activations Density 0.425%

    No Known Activations