© 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. 6-RES-JB
    11. 13669
    Prev
    Next
    INDEX
    Explanations

    sentence structures in the form "verb + subject + rest of sentence"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "did" and its variations, focusing on actions performed in the past

    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
    WARN
    -0.65
    cipled
    -0.64
     WWF
    -0.62
    Topics
    -0.62
     Stra
    -0.60
    bent
    -0.60
     Autob
    -0.59
     Det
    -0.58
     Iss
    -0.58
    theless
    -0.57
    POSITIVE LOGITS
    pez
    1.05
    oms
    0.85
    zed
    0.80
    berman
    0.75
    adian
    0.74
    ggy
    0.73
    onga
    0.73
    lege
    0.70
    zing
    0.70
    omsday
    0.69
    Activations Density 0.058%

    No Known Activations