© 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. 4-RES-JB
    11. 15286
    Prev
    Next
    INDEX
    Explanations

    locations related to the state of Massachusetts in the United States

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Massachusetts

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

    No Comments

    Negative Logits
    sem
    -0.87
    vel
    -0.83
    BOOK
    -0.80
    pter
    -0.78
    loading
    -0.78
    cember
    -0.77
    blem
    -0.74
    ebus
    -0.74
    loaded
    -0.73
    vous
    -0.72
    POSITIVE LOGITS
    achusetts
    1.06
     Massachusetts
    0.85
     Lowell
    0.85
     Bay
    0.83
     Andromeda
    0.81
     Volunteers
    0.78
     Governor
    0.77
     Institute
    0.77
     Conn
    0.76
     Yard
    0.75
    Activations Density 0.014%

    No Known Activations