© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21059
    Prev
    Next
    INDEX
    Explanations

    phrases related to judgment or assessment

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of actions and situations that are misleading or inadequately represented

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    killers
    -0.92
    izons
    -0.91
    ravings
    -0.83
    acers
    -0.82
    ptoms
    -0.78
     dates
    -0.78
     faults
    -0.77
    appings
    -0.77
    aunts
    -0.77
    Tags
    -0.76
    POSITIVE LOGITS
     manner
    1.69
     fashion
    1.47
     vein
    1.31
     context
    1.30
     nutshell
    1.29
     hurry
    1.24
     environment
    1.19
     guise
    1.17
     way
    1.16
     sense
    1.11
    Activations Density 0.223%

    No Known Activations