© 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. 18232
    Prev
    Next
    INDEX
    Explanations

    technical terms related to language processing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spoken language and data processing

    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
    phas
    -0.85
    quit
    -0.80
    ĪĴ
    -0.76
    clerosis
    -0.74
    redit
    -0.71
    pid
    -0.71
    ysis
    -0.71
    ften
    -0.71
    apa
    -0.71
    ayn
    -0.71
    POSITIVE LOGITS
     ones
    0.75
     referen
    0.69
    uction
    0.68
    escription
    0.65
    ucing
    0.64
     geometric
    0.64
    ebted
    0.63
     indu
    0.62
     satell
    0.61
     goods
    0.61
    Activations Density 0.635%

    No Known Activations