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. 3-RES-JB
    6. 21429
    Prev
    Next
    INDEX
    Explanations

    The neuron is searching for phrases related to the effects of various factors or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various effects or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istg
    -0.71
     ILCS
    -0.66
     corners
    -0.63
    anu
    -0.62
    Upload
    -0.62
    eder
    -0.61
    dayName
    -0.61
    querade
    -0.59
    ws
    -0.58
     reperto
    -0.58
    POSITIVE LOGITS
     sorts
    0.88
     ours
    0.75
     course
    0.74
    icial
    0.68
     mankind
    0.68
     these
    0.65
     theirs
    0.65
     obtaining
    0.64
    emale
    0.63
     both
    0.63
    Activations Density 0.402%

    No Known Activations