© 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. 9-RES-JB
    11. 16470
    Prev
    Next
    INDEX
    Explanations

    phrases related to relocations or movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to locations and actions involving movement or transfers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.59
    pires
    -0.59
     geek
    -0.57
     boasts
    -0.56
     Rhythm
    -0.55
     obsessed
    -0.55
     buzzing
    -0.54
     fascination
    -0.54
     fret
    -0.53
     roared
    -0.53
    POSITIVE LOGITS
     ASAP
    1.07
    instead
    0.99
     accordingly
    0.95
    .''.
    0.85
     instead
    0.82
     appropriate
    0.79
    ?".
    0.77
    .�
    0.77
    ''.
    0.77
    .''
    0.75
    Activations Density 1.316%

    No Known Activations