© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14032
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology products and releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain multiple references to "the" followed by various nouns or related concepts

    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
    -0.69
    Scotland
    -0.69
    iberal
    -0.68
     argues
    -0.67
    aji
    -0.67
    sted
    -0.66
    nesty
    -0.66
    .''
    -0.66
    verson
    -0.66
     UNCLASSIFIED
    -0.65
    POSITIVE LOGITS
     aforementioned
    1.29
     latest
    1.25
     same
    1.17
     newest
    1.15
     latter
    1.11
     remainder
    1.09
     entirety
    1.08
     upcoming
    1.07
     coolest
    1.06
     entire
    1.01
    Activations Density 0.933%

    No Known Activations