© 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. 9-RES-JB
    11. 2974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intensity or extremes

    oai_token-act-pair · gpt-3.5-turbo

    instances where "even the most" is used to emphasize a point

    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
    anwhile
    -0.76
    chnology
    -0.75
    along
    -0.73
    terday
    -0.67
    ahime
    -0.66
    aliation
    -0.66
    essa
    -0.66
    eu
    -0.64
    rend
    -0.63
    VERTISEMENT
    -0.63
    POSITIVE LOGITS
     smallest
    1.12
     slightest
    1.09
     curs
    1.08
     modest
    0.97
     innocuous
    0.97
     mundane
    0.97
     simplest
    0.96
     rudimentary
    0.94
     seasoned
    0.88
     mild
    0.88
    Activations Density 0.136%

    No Known Activations