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. 22790
    Prev
    Next
    INDEX
    Explanations

    the concept of something reducing in size or scale

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or decrease in size or quantity

    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
    POL
    -0.79
    role
    -0.72
    ":[{"
    -0.63
    raid
    -0.63
    Ale
    -0.62
    ixture
    -0.62
    orneys
    -0.61
    Princ
    -0.60
    election
    -0.59
    ixtures
    -0.59
    POSITIVE LOGITS
     violet
    0.85
    glers
    0.84
    downs
    0.81
    eness
    0.81
     shrinking
    0.81
    shr
    0.81
    abies
    0.80
     shrink
    0.78
    ular
    0.78
    escent
    0.78
    Activations Density 0.016%

    No Known Activations