© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 150
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a geographic location, specifically "Lake" with different variations and contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific lakes and their names

    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
     tremend
    -0.87
    nir
    -0.86
    */(
    -0.79
    imental
    -0.76
    endiary
    -0.75
    AAAAAAAA
    -0.75
    ulously
    -0.74
    nesday
    -0.72
    ulate
    -0.68
    senal
    -0.68
    POSITIVE LOGITS
     Erie
    1.03
     Lake
    0.93
     trout
    0.91
    front
    0.89
    wood
    0.87
     Superior
    0.86
     Lakes
    0.85
     Creek
    0.83
     Nile
    0.83
     Shore
    0.83
    Activations Density 0.012%

    No Known Activations