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. 6-RES-JB
    6. 8025
    Prev
    Next
    INDEX
    Explanations

    phrases depicting physical locations where someone is standing

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "standing in" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redes
    -0.67
    DL
    -0.64
    elf
    -0.64
    essor
    -0.64
    killed
    -0.63
    catentry
    -0.61
    llor
    -0.61
    soever
    -0.60
    =""
    -0.59
    ŀ
    -0.59
    POSITIVE LOGITS
    ordinate
    1.13
     accordance
    1.04
     front
    1.01
    roads
    0.95
     lieu
    0.95
    animate
    0.94
     unison
    0.92
     spite
    0.91
     conjunction
    0.91
    clud
    0.90
    Activations Density 0.186%

    No Known Activations