© 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. 0-RES-JB
    11. 2485
    Prev
    Next
    INDEX
    Explanations

    powerful and lasting impressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to overall impressions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zah
    -0.67
    byss
    -0.66
    within
    -0.66
    comm
    -0.65
    YC
    -0.61
    ITED
    -0.60
     collapsed
    -0.60
     Forestry
    -0.59
     outlawed
    -0.58
    cedes
    -0.58
    POSITIVE LOGITS
     impression
    3.84
     impressions
    3.78
     imitation
    1.16
     opinion
    1.12
     imperson
    1.09
     appearance
    1.09
     perceptions
    1.09
     imprint
    1.08
     impressed
    1.04
     perception
    1.01
    Activations Density 0.015%

    No Known Activations