© 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. 7-RES-JB
    11. 12401
    Prev
    Next
    INDEX
    Explanations

    phrases related to making changes or taking action

    oai_token-act-pair · gpt-3.5-turbo

    significant changes or updates to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    die
    -0.64
     manif
    -0.57
     drowned
    -0.55
     therein
    -0.54
     attm
    -0.53
     die
    -0.53
    opian
    -0.53
     died
    -0.52
     Others
    -0.51
     Died
    -0.50
    POSITIVE LOGITS
     licensing
    0.69
     hiring
    0.69
     enforcing
    0.67
     FOIA
    0.64
     investigating
    0.64
     prosecuting
    0.64
     hires
    0.61
     issuing
    0.61
     outsourcing
    0.60
     backlog
    0.60
    Activations Density 1.227%

    No Known Activations