© 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. 10-RES-JB
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    actions related to investigation and punishment

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with accountability and legal actions against individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veland
    -0.67
    hene
    -0.66
    Downloadha
    -0.63
    albeit
    -0.63
    >)
    -0.61
    ebus
    -0.59
     MPG
    -0.58
    Champ
    -0.58
    Sync
    -0.58
    eret
    -0.58
    POSITIVE LOGITS
     any
    1.27
     anyone
    1.22
     offenders
    1.22
     whoever
    1.19
     every
    1.14
     whichever
    1.13
     all
    1.13
     offending
    1.11
     ANY
    1.10
     EVERY
    1.07
    Activations Density 0.550%

    No Known Activations