© 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. 11-RES-JB
    11. 6975
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "pad" in various contexts, including geographical, technological, and physical items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orget
    -0.62
     Greater
    -0.61
     Samar
    -0.59
    ously
    -0.58
     framed
    -0.57
    ãĤ¤ãĥĪ
    -0.57
     Ivy
    -0.57
     Ultron
    -0.56
     outp
    -0.55
     victim
    -0.55
    POSITIVE LOGITS
    awan
    1.29
    lock
    0.93
    locked
    0.91
    illa
    0.90
    agon
    0.89
    hao
    0.87
     Thai
    0.87
    ilion
    0.85
    locks
    0.85
    boa
    0.85
    Activations Density 0.046%

    No Known Activations