© 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. 7606
    Prev
    Next
    INDEX
    Explanations

    references to events or locations related to a "Seminar."

    oai_token-act-pair · gpt-3.5-turbo

    references to "semifinals" in various contexts

    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
     evade
    -0.78
    raft
    -0.75
    illed
    -0.75
     obstruct
    -0.72
     obstruction
    -0.69
     restraint
    -0.68
    olson
    -0.67
     repeal
    -0.66
     pirate
    -0.66
    iller
    -0.65
    POSITIVE LOGITS
     Sem
    3.91
    Sem
    2.90
    sem
    2.25
     Semi
    1.59
     sem
    1.53
     SEM
    1.52
     Quarter
    1.22
     Slav
    1.20
     semif
    1.16
     Semin
    1.15
    Activations Density 0.022%

    No Known Activations