© 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. 1-RES-JB
    11. 6723
    Prev
    Next
    INDEX
    Explanations

    terms related to development and embryonic conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to developmental topics, particularly concerning children and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.87
    ñ
    -0.80
    Ń·
    -0.78
    andra
    -0.76
    zzo
    -0.76
    zzi
    -0.71
    yre
    -0.70
    rage
    -0.67
    vard
    -0.66
    zzle
    -0.66
    POSITIVE LOGITS
     developmental
    1.16
     milestones
    0.83
     enrichment
    0.82
     ende
    0.74
     disabilities
    0.74
     evaluations
    0.71
     defects
    0.71
     embry
    0.71
     strugg
    0.70
    mental
    0.70
    Activations Density 0.010%

    No Known Activations