© 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. 842
    Prev
    Next
    INDEX
    Explanations

    references to 'bar' as in a location or a measure, not as in the 'bar' symbol

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a "bar."

    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
    lihood
    -0.91
     Disorder
    -0.79
    IBLE
    -0.78
     Languages
    -0.76
    UAL
    -0.75
    éĹĺ
    -0.74
     Scarlet
    -0.73
     Instruments
    -0.71
    IGHTS
    -0.71
     Vehicles
    -0.71
    POSITIVE LOGITS
    itone
    1.31
    celona
    1.19
    bara
    1.11
    bell
    1.11
    iatric
    1.04
    becue
    0.94
    onial
    0.93
    bed
    0.92
    keep
    0.91
    bour
    0.91
    Activations Density 0.016%

    No Known Activations