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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 18294
    Prev
    Next
    INDEX
    Explanations

    words related to the process of thawing or thickness

    oai_token-act-pair · gpt-3.5-turbo

    various verb forms, particularly related to the concept of "thawing" or "softening."

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

    No Comments

    Negative Logits
    KT
    -0.70
    ãĤ«
    -0.68
    BRE
    -0.68
     Khe
    -0.67
    Hunt
    -0.66
    EX
    -0.66
    ei
    -0.66
    JR
    -0.65
    isSpecialOrderable
    -0.64
     Ced
    -0.64
    POSITIVE LOGITS
    creen
    0.87
     marrow
    0.80
    combe
    0.77
    cture
    0.76
    worms
    0.75
     immersion
    0.74
     electroly
    0.73
     porous
    0.72
     recomb
    0.71
     shalt
    0.70
    Activations Density 0.060%

    No Known Activations