© 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. 17068
    Prev
    Next
    INDEX
    Explanations

    pieces of text referring to attention and different associated contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Attention."

    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
    20439
    -0.80
    FTWARE
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    çĦ
    -0.69
    REDACTED
    -0.68
     Rwanda
    -0.67
    姫
    -0.65
    76561
    -0.65
     Bene
    -0.63
     sliding
    -0.63
    POSITIVE LOGITS
    etic
    1.09
    ention
    1.08
    anooga
    1.05
    ension
    1.04
    ert
    1.03
    ributes
    1.00
    ributed
    0.99
    oir
    0.98
    anas
    0.97
    assin
    0.97
    Activations Density 0.006%

    No Known Activations