© 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. 10-RES-JB
    11. 12108
    Prev
    Next
    INDEX
    Explanations

    words related to packing or being crammed tightly together

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateur
    -0.79
    shire
    -0.78
    tein
    -0.71
     derive
    -0.70
     Parables
    -0.66
    want
    -0.64
    bc
    -0.62
    alties
    -0.61
    Ĥİ
    -0.61
    arb
    -0.59
    POSITIVE LOGITS
    packed
    1.01
     onto
    0.98
     into
    0.96
     bags
    0.92
     shelves
    0.91
     packed
    0.90
     crates
    0.89
    llah
    0.85
    rette
    0.85
     together
    0.82
    Activations Density 0.055%

    No Known Activations