Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5064
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of the word "stall"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "stall" in various contexts

    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
    */(
    -0.81
    vernment
    -0.78
    vironment
    -0.76
     predetermined
    -0.72
    çīĪ
    -0.71
     scripted
    -0.70
    âĵĺ
    -0.69
    ortium
    -0.68
    éĹĺ
    -0.68
    zbek
    -0.67
    POSITIVE LOGITS
    ioned
    1.08
    ions
    1.03
     stall
    1.01
     Stall
    0.97
    ion
    0.96
     stalls
    0.93
    bugs
    0.93
    ings
    0.87
    acles
    0.85
    iao
    0.83
    Activations Density 0.012%

    No Known Activations