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. 3589
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating physical proximity or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe sitting arrangements

    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
    catentry
    -0.84
    Ħ¢
    -0.77
    qua
    -0.69
    si
    -0.67
    origin
    -0.66
    ascript
    -0.66
     Flavoring
    -0.65
    quant
    -0.63
    bender
    -0.62
    Semitism
    -0.61
    POSITIVE LOGITS
     desks
    0.83
     seiz
    0.74
     pedest
    0.67
     idle
    0.67
    oin
    0.66
     drawer
    0.65
     ankles
    0.65
     doors
    0.65
     recess
    0.65
     Sussex
    0.64
    Activations Density 0.119%

    No Known Activations