© 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. 6-RES-JB
    11. 14687
    Prev
    Next
    INDEX
    Explanations

    sentences related to hypothetical scenarios or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating hypothetical situations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fighting
    -0.65
    loads
    -0.64
     touring
    -0.63
     praying
    -0.63
     naming
    -0.63
     Writing
    -0.62
     signing
    -0.62
     talking
    -0.61
     inspecting
    -0.60
     Pell
    -0.59
    POSITIVE LOGITS
     suffice
    1.24
    ŃĶ
    0.97
     overshadow
    0.95
     be
    0.94
     prevail
    0.91
     imply
    0.90
     resonate
    0.90
     surely
    0.89
    ©¶æ
    0.89
     doubtless
    0.89
    Activations Density 0.341%

    No Known Activations