© 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. 10-RES-JB
    11. 8491
    Prev
    Next
    INDEX
    Explanations

    words indicating future actions or possibilities

    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
     bruising
    -0.59
     loses
    -0.58
     participates
    -0.58
     capacities
    -0.56
     Twice
    -0.55
     susp
    -0.55
     spor
    -0.55
     prepares
    -0.54
     Reloaded
    -0.54
     conducts
    -0.54
    POSITIVE LOGITS
     involve
    1.01
    iman
    0.77
     consist
    0.76
    ĸļ
    0.74
     reside
    0.74
     lie
    0.72
    isite
    0.72
     entail
    0.69
     involves
    0.69
     rev
    0.69
    Activations Density 0.139%

    No Known Activations