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. 7-RES-JB
    6. 1255
    Prev
    Next
    INDEX
    Explanations

    the phrase "one thing" followed by a statement or observation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty or significant points regarding various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOS
    -0.79
    ULT
    -0.75
    oÄŁ
    -0.71
    76561
    -0.68
    JV
    -0.67
    onz
    -0.66
    ãĥ¼ãĥ
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    bush
    -0.65
    artments
    -0.64
    POSITIVE LOGITS
    iverse
    0.76
     happens
    0.76
     happened
    0.73
     happening
    0.69
     Constantine
    0.64
     stood
    0.64
    worldly
    0.63
     else
    0.62
     separates
    0.61
    icularly
    0.61
    Activations Density 0.035%

    No Known Activations