© 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. 7858
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and bookings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to arrests and incarceration

    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
    natureconservancy
    -0.85
    ahime
    -0.76
    lus
    -0.71
    ulence
    -0.71
    lins
    -0.70
    bugs
    -0.66
     redund
    -0.66
     flavours
    -0.66
    gans
    -0.65
     glitches
    -0.64
    POSITIVE LOGITS
     jail
    1.36
     custody
    1.35
     Detention
    1.27
     Jail
    1.27
     juvenile
    1.18
     jails
    1.14
     Correctional
    1.11
     Juven
    1.10
     detention
    1.10
     courthouse
    1.00
    Activations Density 0.152%

    No Known Activations