© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20336
    Prev
    Next
    INDEX
    Explanations

    the word "exp" in the input text

    oai_token-act-pair · gpt-3.5-turbo

    references to exports or exporting activities

    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
    STEM
    -0.71
    enegger
    -0.71
    WORK
    -0.69
     Luck
    -0.68
     Crom
    -0.67
    GROUND
    -0.64
     Hook
    -0.63
     Freud
    -0.63
     Dreams
    -0.63
    MpServer
    -0.62
    POSITIVE LOGITS
    orters
    1.45
    ropri
    1.37
    orter
    1.23
    ulsion
    1.20
    anse
    1.19
    onents
    1.14
    iry
    1.13
    ittance
    1.13
    uls
    1.11
    iring
    1.09
    Activations Density 0.021%

    No Known Activations