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

    Neuronpedia

    Jacobian LensNEW
    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. 21164
    Prev
    Next
    INDEX
    Explanations

    IP addresses and technical information related to computer networking

    oai_token-act-pair · gpt-3.5-turbo

    numerical IP addresses and related networking terms

    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
     illust
    -0.82
     glim
    -0.76
     graphic
    -0.72
     infographic
    -0.71
     streng
    -0.70
     primer
    -0.70
     indo
    -0.70
    epad
    -0.67
     supplemental
    -0.67
     visual
    -0.66
    POSITIVE LOGITS
    isSpecialOrderable
    0.93
    yards
    0.84
    ourse
    0.75
    jar
    0.75
    park
    0.74
    emetery
    0.71
    services
    0.71
    Lago
    0.70
     sshd
    0.70
    1963
    0.70
    Activations Density 0.051%

    No Known Activations