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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20192
    Prev
    Next
    INDEX
    Explanations

    references to children or issues related to children

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "children" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ced
    -0.72
    PROV
    -0.69
    ENCE
    -0.68
    COMPLE
    -0.66
     comm
    -0.66
    Population
    -0.64
    ATION
    -0.63
    ATIVE
    -0.62
    Sharp
    -0.62
     lame
    -0.60
    POSITIVE LOGITS
    children
    1.02
    ishly
    0.97
    child
    0.85
    arten
    0.81
     children
    0.80
    ults
    0.79
     orphan
    0.79
    riages
    0.77
    mol
    0.77
     Icar
    0.76
    Activations Density 0.041%

    No Known Activations