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. 9-RES-JB
    6. 848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "out"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "handing out" or similar distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antry
    -0.87
    ajor
    -0.78
    isma
    -0.78
    STER
    -0.76
    orrow
    -0.75
    âĢ
    -0.71
    Appearance
    -0.69
    terday
    -0.68
    Gaming
    -0.67
    inity
    -0.67
    POSITIVE LOGITS
     flyers
    1.21
     leaflets
    1.08
     pamph
    1.00
    stretched
    0.99
     invitations
    0.99
    posts
    0.86
     flyer
    0.85
     waivers
    0.85
    spr
    0.77
     copies
    0.76
    Activations Density 0.055%

    No Known Activations