© 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. 24058
    Prev
    Next
    INDEX
    Explanations

    instances where an action or outcome is anticipated or expected

    oai_token-act-pair · gpt-3.5-turbo

    assertions or recommendations related to expectations or necessities

    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
     syndrome
    -0.67
     Syndrome
    -0.67
     Puzzle
    -0.65
     Fra
    -0.63
     Zah
    -0.63
    GGGGGGGG
    -0.60
     Rox
    -0.60
    CI
    -0.59
     Afgh
    -0.58
     Patty
    -0.58
    POSITIVE LOGITS
     ideally
    1.08
     be
    1.04
    ered
    1.04
     theoretically
    0.93
     clarify
    0.87
     suffice
    0.86
    ering
    0.86
    othal
    0.83
    nt
    0.80
    amber
    0.77
    Activations Density 0.063%

    No Known Activations