© 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. 4-RES-JB
    11. 14302
    Prev
    Next
    INDEX
    Explanations

    text related to uninhabited or uninhabitable places

    oai_token-act-pair · gpt-3.5-turbo

    words related to habitation or the concept of living in an environment

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

    No Comments

    Negative Logits
     Chr
    -0.71
     Blessed
    -0.68
    arity
    -0.67
    CHR
    -0.65
    chnology
    -0.65
     amplified
    -0.64
    CHO
    -0.63
    AUT
    -0.62
     rand
    -0.62
     Europeans
    -0.62
    POSITIVE LOGITS
    ilitation
    1.37
    ilit
    1.07
    itual
    1.04
    bing
    1.03
    itable
    1.03
    hab
    1.02
    itant
    1.01
    ilitating
    1.00
    ranch
    0.96
    bed
    0.92
    Activations Density 0.006%

    No Known Activations