© 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. 3331
    Prev
    Next
    INDEX
    Explanations

    the word "carried" with varying degrees of strength

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "carried" 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
    unning
    -0.70
    olutions
    -0.69
     hex
    -0.65
    ellen
    -0.64
    inese
    -0.64
    Filename
    -0.62
    IOR
    -0.62
    ect
    -0.62
    apter
    -0.62
    uber
    -0.62
    POSITIVE LOGITS
     carried
    1.09
     ashore
    0.78
     carry
    0.77
     Held
    0.75
     borne
    0.72
     stret
    0.71
     corrid
    0.71
     Boone
    0.68
     carriers
    0.67
    ĸļ
    0.66
    Activations Density 0.010%

    No Known Activations