© 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. 1-RES-JB
    11. 13300
    Prev
    Next
    INDEX
    Explanations

    combinations or pairs of words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combined" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keeper
    -0.96
    keepers
    -0.87
    yer
    -0.81
    ways
    -0.76
    posts
    -0.74
    writers
    -0.72
    aiden
    -0.71
    bors
    -0.70
    ysis
    -0.70
    yers
    -0.69
    POSITIVE LOGITS
     combined
    0.85
    ãĤ¤ãĥĪ
    0.82
     outputs
    0.79
     sum
    0.75
     redund
    0.75
     thrust
    0.74
     strokes
    0.73
     guiActiveUn
    0.72
     combine
    0.71
     totals
    0.71
    Activations Density 0.009%

    No Known Activations