© 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. 2-RES-JB
    11. 19397
    Prev
    Next
    INDEX
    Explanations

    profane and derogatory terms or insults referring to people

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms and insults directed at individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apers
    -0.77
    tis
    -0.76
    fman
    -0.71
    Ec
    -0.71
    ENC
    -0.70
    orsi
    -0.70
    anship
    -0.68
    uries
    -0.68
    undai
    -0.68
    orthy
    -0.68
    POSITIVE LOGITS
     asses
    1.03
    fuck
    1.02
     bitch
    1.01
     bastard
    1.00
     asshole
    0.99
    holes
    0.93
    hole
    0.91
     idiot
    0.90
     fuck
    0.89
    bags
    0.87
    Activations Density 0.036%

    No Known Activations