© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10351
    Prev
    Next
    INDEX
    Explanations

    names and locations, particularly those involving sports

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific gerunds or verb forms ending in 'ing'

    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
    ihar
    -0.76
    nery
    -0.75
    ngth
    -0.73
    ably
    -0.69
    icles
    -0.68
    uba
    -0.67
    ophob
    -0.66
    igning
    -0.65
    iness
    -0.65
    idity
    -0.65
    POSITIVE LOGITS
    tons
    1.35
    ham
    1.17
    HAM
    1.13
    ton
    1.05
    redients
    0.97
     Stones
    0.96
     Sands
    0.93
    edge
    0.86
    lass
    0.85
    haus
    0.83
    Activations Density 0.119%

    No Known Activations