© 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. 1-RES-JB
    11. 3934
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical structures with enclosed compartments, such as 'stall'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "stall" and its variations, particularly in contexts related to bathrooms or food venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.69
     seismic
    -0.68
    âĵĺ
    -0.68
    ortium
    -0.67
    vironment
    -0.66
     GOODMAN
    -0.64
    çīĪ
    -0.64
    */(
    -0.63
     Occ
    -0.63
    rouse
    -0.63
    POSITIVE LOGITS
     stall
    1.40
     stalls
    1.27
    ioned
    0.99
    wagon
    0.98
     Stall
    0.92
    holders
    0.86
    ion
    0.86
    pieces
    0.85
    bugs
    0.83
     Fitzgerald
    0.80
    Activations Density 0.009%

    No Known Activations