© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15964
    Prev
    Next
    INDEX
    Explanations

    instances where the text contrasts a situation with potential negative implications against something else or raises concerns

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    si
    -0.82
    RIP
    -0.79
    atos
    -0.76
    bowl
    -0.76
    itect
    -0.74
    pecially
    -0.72
    PI
    -0.70
    utm
    -0.68
    ().
    -0.68
    Its
    -0.68
    POSITIVE LOGITS
     nonetheless
    1.04
    etheless
    0.98
     undeniable
    0.80
     nevertheless
    0.76
     deeper
    0.75
    chers
    0.74
     curiously
    0.74
     undeniably
    0.72
     challeng
    0.72
     broader
    0.71
    Activations Density 0.592%

    No Known Activations