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. 1-RES-JB
    6. 1556
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "lighter", such as the physical object, color, or weight

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "lighter" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posted
    -0.81
    0000
    -0.80
    raltar
    -0.79
    VR
    -0.77
    Unknown
    -0.77
    IDENT
    -0.76
    DES
    -0.76
    cert
    -0.74
    CVE
    -0.73
    HI
    -0.72
    POSITIVE LOGITS
     lighter
    1.26
    weights
    1.01
     weights
    0.90
     bulb
    0.88
     heavier
    0.88
     advoc
    0.84
    weight
    0.83
    izont
    0.82
    izontal
    0.81
    iating
    0.80
    Activations Density 0.008%

    No Known Activations