© 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. 11-RES-JB
    11. 18729
    Prev
    Next
    INDEX
    Explanations

    career-related phrases and terms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to crime and the criminal justice system

    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
    CLASSIFIED
    -0.69
     territ
    -0.65
    ELD
    -0.63
    è£ħ
    -0.61
     Carbuncle
    -0.61
    bourg
    -0.56
    alach
    -0.55
     predec
    -0.54
    irable
    -0.54
     concurrently
    -0.53
    POSITIVE LOGITS
     how
    1.14
     why
    1.07
     that
    0.99
     whether
    0.94
    that
    0.92
     THAT
    0.91
    why
    0.90
     WHY
    0.87
     what
    0.86
     HOW
    0.84
    Activations Density 0.570%

    No Known Activations