© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 4870
    Prev
    Next
    INDEX
    Explanations

    words related to simplicity and immediate actions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    themes related to simplicity and minimalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.69
     tracts
    -0.67
     hemisphere
    -0.65
     Federation
    -0.63
    Interstitial
    -0.62
     Stall
    -0.62
    estone
    -0.61
    unes
    -0.60
     Jobs
    -0.59
     wake
    -0.58
    POSITIVE LOGITS
    iness
    1.09
    lessness
    1.07
    terness
    1.00
    jriwal
    0.90
     Flavoring
    0.86
     simplicity
    0.86
    iqueness
    0.85
    fulness
    0.84
    icity
    0.83
    lessly
    0.83
    Activations Density 0.019%

    No Known Activations