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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 22945
    Prev
    Next
    INDEX
    Explanations

    words prefixed with 'un'

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that start with "un-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ajax
    -0.70
     Cree
    -0.66
     FAR
    -0.66
     face
    -0.65
     Tut
    -0.65
     realism
    -0.65
     hinge
    -0.65
     rides
    -0.63
     fixtures
    -0.63
     drawer
    -0.62
    POSITIVE LOGITS
    assuming
    1.37
    cles
    1.37
    apolog
    1.34
    ruly
    1.34
    confirmed
    1.32
    spoken
    1.30
    numbered
    1.29
    character
    1.27
    anticipated
    1.27
    occupied
    1.27
    Activations Density 0.026%

    No Known Activations