© 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. 2-RES-JB
    11. 17621
    Prev
    Next
    INDEX
    Explanations

    references to something being in its entirety

    oai_token-act-pair · gpt-3.5-turbo

    references to the completeness or wholeness of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ging
    -0.71
    ku
    -0.70
    vals
    -0.69
    Anderson
    -0.68
    ker
    -0.66
    verbs
    -0.64
    went
    -0.63
    hy
    -0.61
    fman
    -0.60
    rise
    -0.59
    POSITIVE LOGITS
    ructure
    0.91
     4090
    0.86
    SourceFile
    0.82
    aurus
    0.78
    ï¸
    0.77
     unlaw
    0.76
     guiActiveUn
    0.75
    heartedly
    0.74
    ocument
    0.74
     è£ıè¦ļéĨĴ
    0.74
    Activations Density 0.008%

    No Known Activations