© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    phrases related to holding individuals or groups accountable for actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to societal roles and accountability

    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
    etheless
    -0.76
    itone
    -0.70
    bernatorial
    -0.69
    aturday
    -0.68
    ept
    -0.65
     Lent
    -0.65
    ciating
    -0.63
     unfocusedRange
    -0.63
    gomery
    -0.63
    mn
    -0.61
    POSITIVE LOGITS
     accountable
    1.15
     hostage
    1.03
     obsolete
    0.85
     alive
    0.82
     captive
    0.78
     abl
    0.77
     away
    0.76
     safe
    0.76
     awake
    0.76
     aback
    0.76
    Activations Density 0.316%

    No Known Activations