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. 24176
    Prev
    Next
    INDEX
    Explanations

    words related to contradiction or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrast or alternatives

    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
    TPPStreamerBot
    -0.63
    isphere
    -0.62
     ozone
    -0.59
     miscarriage
    -0.59
     keyboards
    -0.58
    edIn
    -0.58
    Marginal
    -0.57
     kosher
    -0.56
    ivist
    -0.56
     Redemption
    -0.55
    POSITIVE LOGITS
    etheless
    0.94
    anwhile
    0.81
    theless
    0.75
    È
    0.71
    ngth
    0.67
    nces
    0.66
    cephal
    0.65
    icators
    0.64
    ÅŁ
    0.64
    clair
    0.63
    Activations Density 0.165%

    No Known Activations