© 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. 9359
    Prev
    Next
    INDEX
    Explanations

    keywords related to carrying or transporting goods over a distance

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of acquiring or carrying a large quantity of items

    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
    changes
    -0.67
    cussion
    -0.66
    ricular
    -0.63
    ocal
    -0.63
     ellipt
    -0.62
    extremely
    -0.62
    lip
    -0.60
    eon
    -0.59
    culated
    -0.59
     encouraged
    -0.58
    POSITIVE LOGITS
     haul
    1.49
    loads
    0.95
     hauled
    0.88
     Bagg
    0.81
    igslist
    0.77
    bags
    0.75
    enger
    0.74
    load
    0.73
    ortment
    0.73
    aways
    0.72
    Activations Density 0.004%

    No Known Activations