© 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. 23875
    Prev
    Next
    INDEX
    Explanations

    instances where individuals come forward with information or accusations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals coming forward to report abuses or accusations

    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
     guiActiveUnfocused
    -0.91
    ebus
    -0.85
    bred
    -0.75
    becue
    -0.74
    Style
    -0.72
    ahime
    -0.72
     brisk
    -0.71
    gob
    -0.70
    lot
    -0.69
    ffee
    -0.69
    POSITIVE LOGITS
     testimonies
    1.26
     allegations
    1.09
     alleges
    1.08
     survivors
    1.07
     allege
    1.06
     complain
    1.04
     whistleblowers
    1.02
     anonymously
    1.02
     corrobor
    1.02
     witnesses
    1.01
    Activations Density 0.288%

    No Known Activations