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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8246
    Prev
    Next
    INDEX
    Explanations

    specific mentions of something being wrapped or packaged

    oai_token-act-pair · gpt-3.5-turbo
    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
    upon
    -0.87
    alty
    -0.74
    sych
    -0.72
    tics
    -0.72
    tical
    -0.72
    orie
    -0.68
    rade
    -0.68
    oi
    -0.67
    die
    -0.67
    farious
    -0.67
    POSITIVE LOGITS
     wrapping
    1.09
     wrapped
    1.05
    adoes
    1.04
     wrap
    0.98
    wrap
    0.91
     wraps
    0.88
     shroud
    0.88
     envelop
    0.82
    nesday
    0.81
    NetMessage
    0.77
    Activations Density 0.010%

    No Known Activations