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. 19312
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to expressing necessity or requirement

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "need" in various contexts

    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
    gdala
    -0.61
     rigged
    -0.61
     quir
    -0.60
     skiing
    -0.59
     Tuls
    -0.58
     rabbit
    -0.56
    creen
    -0.56
     Magnum
    -0.56
     Carbuncle
    -0.56
     corrid
    -0.56
    POSITIVE LOGITS
    lessly
    1.23
    onies
    0.79
    lest
    0.79
    iness
    0.74
    liest
    0.72
    acy
    0.70
    Gaming
    0.69
    Compat
    0.66
    igslist
    0.66
    oppers
    0.65
    Activations Density 0.057%

    No Known Activations