© 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. 2-RES-JB
    11. 16948
    Prev
    Next
    INDEX
    Explanations

    terms related to recognition, such as "recognition," "official recognition," and "recognition that."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acknowledgment or validation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grind
    -0.65
    orld
    -0.64
     Ruff
    -0.64
    yss
    -0.62
     inj
    -0.59
    Blog
    -0.59
     Roof
    -0.58
     Quin
    -0.57
     reck
    -0.57
     Antar
    -0.57
    POSITIVE LOGITS
     recognition
    1.06
    ibility
    0.98
    DragonMagazine
    0.95
    recogn
    0.95
     recognizing
    0.93
     recognize
    0.84
    ably
    0.82
    itarian
    0.81
     recognise
    0.80
    ability
    0.79
    Activations Density 0.012%

    No Known Activations