© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7887
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemistry and molecular biology, particularly focusing on specific protein expressions and processes within the brain

    oai_token-act-pair · gpt-3.5-turbo

    references to neurobiology and specific brain structures or mechanisms

    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
     Homes
    -0.74
     applause
    -0.73
     Ike
    -0.72
     cheered
    -0.72
    Jimmy
    -0.72
     anniversary
    -0.70
     Roose
    -0.69
     veto
    -0.67
     ensu
    -0.67
     Pledge
    -0.66
    POSITIVE LOGITS
     hypothesized
    1.02
     biologically
    1.00
     endogenous
    1.00
     âĪ¼
    0.99
     (âĪĴ
    0.98
     molecular
    0.96
     neuronal
    0.95
     cortical
    0.95
     anatomical
    0.94
     quantitative
    0.94
    Activations Density 2.171%

    No Known Activations