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. 3-RES-JB
    6. 6868
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical terms in physics and engineering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to abstraction and conceptualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accountability
    -0.71
     Own
    -0.70
     Lines
    -0.66
     Payments
    -0.59
     Yard
    -0.58
     Prediction
    -0.58
     Commons
    -0.57
     Applicant
    -0.57
     Liberties
    -0.56
     Realms
    -0.56
    POSITIVE LOGITS
    ioned
    0.68
    ettes
    0.68
    ensis
    0.66
    iped
    0.65
    id
    0.65
    iously
    0.63
    hed
    0.62
    oop
    0.62
    oots
    0.62
    azine
    0.62
    Activations Density 0.603%

    No Known Activations