© 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. 0-RES-JB
    11. 9771
    Prev
    Next
    INDEX
    Explanations

    terms related to demolition or destruction

    oai_token-act-pair · gpt-3.5-turbo

    terms related to demolition and destruction of structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itized
    -0.71
    kiss
    -0.69
    externalActionCode
    -0.66
    displayText
    -0.66
     KS
    -0.65
    Menu
    -0.65
     HIP
    -0.64
    Virgin
    -0.64
     Rewards
    -0.64
    stretched
    -0.63
    POSITIVE LOGITS
     demol
    3.07
     demolition
    2.43
     demolished
    1.87
     bulldo
    1.18
    unker
    1.10
     debunk
    1.04
    olition
    0.98
    zhen
    0.96
    berman
    0.92
     dismant
    0.92
    Activations Density 0.033%

    No Known Activations