Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14494
    Prev
    Next
    INDEX
    Explanations

    phrases related to implicit or tacit knowledge, biases, or admissions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to implicit biases and underlying assumptions

    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
    ishers
    -0.79
    mir
    -0.76
    akura
    -0.76
    gard
    -0.75
    ĪĴ
    -0.74
     Vid
    -0.73
    tis
    -0.69
    ppa
    -0.68
    cake
    -0.68
    affles
    -0.68
    POSITIVE LOGITS
    icit
    1.00
     guiActiveUn
    0.99
     implicitly
    0.97
     assumption
    0.94
     tacit
    0.94
     consent
    0.93
     implicit
    0.92
     inference
    0.84
     induct
    0.81
     induction
    0.80
    Activations Density 0.012%

    No Known Activations