Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 276
    Prev
    Next
    INDEX
    Explanations

    places where people live

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating residency or living situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elight
    -0.81
    oug
    -0.70
    sonian
    -0.69
    ²¾
    -0.67
    xual
    -0.65
    aptic
    -0.64
    ery
    -0.63
    ause
    -0.63
    iasis
    -0.60
    AAF
    -0.60
    POSITIVE LOGITS
     upstairs
    0.97
     downstairs
    0.94
     paycheck
    0.94
    chool
    0.92
     vic
    0.91
     abroad
    0.85
     nearby
    0.82
     comfortably
    0.82
     peacefully
    0.79
     near
    0.79
    Activations Density 0.036%

    No Known Activations