© 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. 3963
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals

    oai_token-act-pair · gpt-3.5-turbo

    references to academic journals

    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
    BuyableInstoreAndOnline
    -0.74
    rises
    -0.71
    ucha
    -0.68
    rav
    -0.66
    chuk
    -0.66
    cream
    -0.65
    isin
    -0.65
     Afgh
    -0.64
    byn
    -0.62
     Yin
    -0.61
    POSITIVE LOGITS
     journal
    1.31
     journals
    1.11
     papers
    1.03
     Journals
    0.96
    ournals
    0.93
    Paper
    0.85
    Journal
    0.82
     paper
    0.82
     Papers
    0.82
    ļéĨĴ
    0.80
    Activations Density 0.012%

    No Known Activations