© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    instances where a person arrives or is currently located in a specific place

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or places

    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
    catentry
    -0.62
    Medical
    -0.61
    visors
    -0.61
    regate
    -0.59
    omore
    -0.59
    paralle
    -0.59
    Doctors
    -0.58
    ####
    -0.58
    Mail
    -0.58
    UTH
    -0.58
    POSITIVE LOGITS
    abouts
    1.36
    tics
    1.35
    tical
    1.33
    tic
    1.22
    fires
    0.72
    here
    0.69
    trak
    0.67
     assembled
    0.67
    yers
    0.67
    inel
    0.65
    Activations Density 0.051%

    No Known Activations