© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19137
    Prev
    Next
    INDEX
    Explanations

    proper nouns or words related to the city of Hoboken

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, particularly "Hoboken" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    course
    -0.76
    national
    -0.72
    his
    -0.72
    husband
    -0.71
    claim
    -0.70
     scrut
    -0.67
    court
    -0.66
     plots
    -0.65
     Males
    -0.64
    wife
    -0.63
    POSITIVE LOGITS
    oken
    4.38
    hin
    1.73
     Conan
    0.97
    anka
    0.97
    akening
    0.91
    aido
    0.91
    inki
    0.89
    atform
    0.87
    onen
    0.86
    akens
    0.85
    Activations Density 0.030%

    No Known Activations