© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14403
    Prev
    Next
    INDEX
    Explanations

    future hypothetical scenarios or questions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and inquiries about future possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tesy
    -0.72
    onz
    -0.72
    lication
    -0.70
    vati
    -0.67
    iard
    -0.64
     Asked
    -0.60
    claimer
    -0.60
     Examination
    -0.60
     Talks
    -0.60
    inen
    -0.59
    POSITIVE LOGITS
     happen
    1.64
     motivate
    1.16
     happened
    1.15
     happ
    1.11
     happens
    1.10
     occur
    1.06
     transpired
    1.05
     constitute
    1.04
     Happ
    0.96
     characterize
    0.88
    Activations Density 0.091%

    No Known Activations