© 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. 4-RES-JB
    11. 11411
    Prev
    Next
    INDEX
    Explanations

    questions ending with question marks

    oai_token-act-pair · gpt-3.5-turbo

    questions in the text

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

    No Comments

    Negative Logits
    apers
    -0.73
     limbs
    -0.70
    aper
    -0.69
     locks
    -0.67
     pace
    -0.66
     towels
    -0.65
     padded
    -0.65
     breeze
    -0.65
     towel
    -0.64
     tentacles
    -0.64
    POSITIVE LOGITS
     Answer
    1.05
     inquired
    0.91
     Inqu
    0.89
     Questions
    0.87
     Asked
    0.85
     asks
    0.83
     Huh
    0.82
    Answer
    0.79
    #$
    0.79
     Why
    0.78
    Activations Density 0.012%

    No Known Activations