© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 622
    Prev
    Next
    INDEX
    Explanations

    words related to persistence or continuation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to previous actions or references

    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
     Barnett
    -0.72
    beit
    -0.71
     guiActiveUn
    -0.71
     distortions
    -0.69
    raq
    -0.69
    ysis
    -0.69
    ettes
    -0.68
     nods
    -0.67
    hya
    -0.66
     McKenna
    -0.66
    POSITIVE LOGITS
    prev
    0.92
     [+
    0.82
     surv
    0.80
    iral
    0.78
     Prev
    0.76
    ħ
    0.75
     NEXT
    0.72
    noon
    0.70
    ebin
    0.70
    dest
    0.70
    Activations Density 0.010%

    No Known Activations