© 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. 8-RES-JB
    11. 24124
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "snitching" or related actions

    oai_token-act-pair · gpt-3.5-turbo

    words that start with "sn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.96
    shire
    -0.71
    xual
    -0.69
    EMENT
    -0.68
     limited
    -0.65
     Britann
    -0.64
    WAYS
    -0.60
     Bachelor
    -0.60
    minus
    -0.59
    geist
    -0.59
    POSITIVE LOGITS
    agging
    1.21
    appy
    1.20
    ugg
    1.19
    obb
    1.17
    ipes
    1.16
    atching
    1.16
    appers
    1.14
    atches
    1.13
    apper
    1.11
    apping
    1.11
    Activations Density 0.020%

    No Known Activations