© 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. 17793
    Prev
    Next
    INDEX
    Explanations

    terms related to financial support or sponsorship

    oai_token-act-pair · gpt-3.5-turbo

    references to backers and supporters in a funding context

    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
     Virus
    -0.68
    odor
    -0.67
     Maw
    -0.67
    Naz
    -0.66
     Sed
    -0.63
     Darwin
    -0.63
    uba
    -0.62
    cer
    -0.62
    apy
    -0.62
    uku
    -0.61
    POSITIVE LOGITS
     backers
    1.28
     backer
    1.17
    Supporters
    0.89
    nuts
    0.87
    backer
    0.86
     supporters
    0.84
    interstitial
    0.80
    ervatives
    0.78
    ervative
    0.77
     Supporters
    0.76
    Activations Density 0.010%

    No Known Activations