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. 0-RES-JB
    6. 3540
    Prev
    Next
    INDEX
    Explanations

    phrases related to the organization "Ofsted"

    oai_token-act-pair · gpt-3.5-turbo

    references to inspections or evaluations conducted by an organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remote
    -0.72
     impulse
    -0.69
     flashes
    -0.65
     recoil
    -0.63
     shots
    -0.63
     suppress
    -0.63
     memory
    -0.62
     swap
    -0.61
     pool
    -0.61
     auto
    -0.61
    POSITIVE LOGITS
    sted
    5.08
    stead
    1.44
    stad
    1.41
    vier
    1.21
    stadt
    1.20
    strom
    1.15
    gged
    1.03
    atche
    1.01
    nces
    0.99
    quist
    0.99
    Activations Density 0.007%

    No Known Activations