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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 17924
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or material properties

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to properties and characteristics of various subjects, particularly in scientific 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
    icago
    -0.78
    bone
    -0.72
    atre
    -0.71
    scl
    -0.68
    sie
    -0.66
    ILLE
    -0.65
    overs
    -0.63
    avez
    -0.63
    ansen
    -0.63
    sis
    -0.62
    POSITIVE LOGITS
     properties
    1.07
    properties
    0.85
     Properties
    0.80
    unctions
    0.77
    ality
    0.73
    uation
    0.70
    ter
    0.70
    ECT
    0.68
    raits
    0.67
    adata
    0.67
    Activations Density 0.012%

    No Known Activations