© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 4096
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts associated with time and the past

    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
    SPONSORED
    -0.66
    vernment
    -0.62
    meric
    -0.60
    bots
    -0.59
    opausal
    -0.58
    atto
    -0.58
     according
    -0.58
    iac
    -0.58
    bis
    -0.57
     Supports
    -0.56
    POSITIVE LOGITS
     forefront
    1.03
     same
    1.02
     proverbial
    1.01
     slightest
    0.99
     simplest
    0.95
     margins
    0.94
     periphery
    0.92
     depths
    0.91
     utmost
    0.91
     usual
    0.89
    Activations Density 0.618%

    No Known Activations