© 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. 11355
    Prev
    Next
    INDEX
    Explanations

    phrases related to architecture and hierarchical organization

    oai_token-act-pair · gpt-3.5-turbo

    references to high-rise structures and related terminology

    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
     Anth
    -0.71
    =-=-=-=-
    -0.69
     remotely
    -0.67
    qt
    -0.66
     hither
    -0.63
    gey
    -0.62
    EStream
    -0.62
     Became
    -0.62
    iar
    -0.60
    orus
    -0.59
    POSITIVE LOGITS
    enser
    0.71
     denomination
    0.70
    inence
    0.70
     Pradesh
    0.69
    entin
    0.68
    urances
    0.67
    eanor
    0.67
    standing
    0.67
    urance
    0.67
    etheless
    0.67
    Activations Density 0.352%

    No Known Activations