© 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. 2296
    Prev
    Next
    INDEX
    Explanations

    phrases related to relocation or shifting of physical objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the transfer or relocation of individuals or entities

    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
    rawdownloadcloneembedreportprint
    -0.68
    icious
    -0.61
     Coup
    -0.59
     betrayal
    -0.58
     nails
    -0.58
     twists
    -0.56
     leaflets
    -0.55
     ANN
    -0.55
     slightest
    -0.55
     flares
    -0.55
    POSITIVE LOGITS
    livion
    1.00
     footing
    0.83
     ASAP
    0.74
     mode
    0.74
    Zone
    0.71
     instead
    0.71
    dominated
    0.64
    next
    0.63
    instead
    0.63
    mode
    0.63
    Activations Density 0.586%

    No Known Activations