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

    Neuronpedia

    Jacobian LensNEW
    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. 14963
    Prev
    Next
    INDEX
    Explanations

    words related to harmful actions or events and their consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to crime and its consequences

    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
    ================================
    -0.61
     Lets
    -0.59
     Majesty
    -0.59
     advoc
    -0.57
    ¯¯¯¯¯¯¯¯
    -0.57
    idth
    -0.55
     Whilst
    -0.53
    BuyableInstoreAndOnline
    -0.53
     Bachelor
    -0.52
     Tuls
    -0.52
    POSITIVE LOGITS
     afterward
    1.28
     afterwards
    1.01
     elsewhere
    0.98
     later
    0.93
     thereafter
    0.82
     earlier
    0.79
     abroad
    0.79
     nearby
    0.78
    Enlarge
    0.77
     beforehand
    0.71
    Activations Density 0.617%

    No Known Activations