© 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. 9-RES-JB
    11. 17686
    Prev
    Next
    INDEX
    Explanations

    words related to captivation and control

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to captivity or being held by others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.69
     Catalyst
    -0.67
     partnership
    -0.64
    senal
    -0.64
    BI
    -0.64
     trust
    -0.62
     bureaucracy
    -0.60
     pregnancy
    -0.59
     spare
    -0.59
     Shattered
    -0.58
    POSITIVE LOGITS
    ivating
    1.41
    ained
    1.40
    ains
    1.33
    aining
    1.28
    ions
    1.24
    ivated
    1.23
    urable
    1.12
    ured
    1.08
    oise
    1.05
    ainer
    1.05
    Activations Density 0.031%

    No Known Activations