© 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. 0-RES-JB
    6. 2200
    Prev
    Next
    INDEX
    Explanations

    words related to exotic weaponry

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exotic or unusual characteristics 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
     backlog
    -0.62
     salaries
    -0.61
     RBI
    -0.60
     math
    -0.60
     Meteor
    -0.59
     delegate
    -0.58
     Accountability
    -0.58
     FINAL
    -0.58
     EAR
    -0.58
     lod
    -0.58
    POSITIVE LOGITS
    otic
    4.59
    otics
    3.37
    osis
    2.27
    otes
    1.55
    ote
    1.32
    ostic
    1.29
    oses
    1.25
    ogenic
    1.22
    ots
    1.18
    ot
    1.15
    Activations Density 0.012%

    No Known Activations