© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    words related to negative or disrespectful language and behavior

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disrespect and negative connotations

    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
    ulhu
    -0.75
    Phones
    -0.72
    ailability
    -0.71
    essage
    -0.69
    ECK
    -0.67
    iqueness
    -0.65
    hower
    -0.65
    angler
    -0.64
    Kings
    -0.62
    Introduced
    -0.61
    POSITIVE LOGITS
     towards
    1.38
     toward
    1.38
     to
    0.94
     thereto
    0.93
     unto
    0.84
    ctive
    0.80
     enough
    0.76
     thereof
    0.74
     Towards
    0.74
     sidx
    0.73
    Activations Density 0.138%

    No Known Activations