© 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. 8-RES-JB
    11. 7103
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or progression from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence or reference to previous information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.69
    HH
    -0.66
    aah
    -0.66
     Bundy
    -0.65
    %%%%
    -0.64
     Nationals
    -0.61
    rongh
    -0.61
    YES
    -0.60
     Zin
    -0.60
    natureconservancy
    -0.59
    POSITIVE LOGITS
     onwards
    1.26
     onward
    1.15
    forward
    0.80
    idate
    0.76
    annis
    0.76
     sprang
    0.75
    forth
    0.72
    oded
    0.72
    iral
    0.71
    awaru
    0.69
    Activations Density 0.041%

    No Known Activations