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. 4-RES-JB
    6. 19203
    Prev
    Next
    INDEX
    Explanations

    text related to camels and caramel

    oai_token-act-pair · gpt-3.5-turbo

    terms related to camels and various forms of caramel

    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
    alez
    -0.88
     Compton
    -0.81
    went
    -0.78
    cture
    -0.77
    lus
    -0.75
    space
    -0.70
    rup
    -0.68
     Asgard
    -0.68
    kson
    -0.68
    ession
    -0.67
    POSITIVE LOGITS
    amel
    1.05
    opard
    0.94
    ises
    0.86
    ãĤ¨ãĥ«
    0.83
    ised
    0.82
    ized
    0.81
    toe
    0.80
    isable
    0.78
    piece
    0.78
     camel
    0.77
    Activations Density 0.023%

    No Known Activations