© 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. 2-RES-JB
    11. 5980
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "nesting" or objects being nested within each other

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nesting and habitation

    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
    Primary
    -0.79
    VERSION
    -0.72
    WAYS
    -0.69
     physical
    -0.66
     muscular
    -0.66
    vation
    -0.65
    ×ķ
    -0.64
     Literature
    -0.64
    BILITY
    -0.64
    primary
    -0.63
    POSITIVE LOGITS
     nest
    1.20
    eers
    0.98
    lace
    0.95
     nests
    0.93
    arus
    0.87
    edIn
    0.86
    acle
    0.82
    lings
    0.82
     Nest
    0.81
    ertodd
    0.81
    Activations Density 0.004%

    No Known Activations