© 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. 0-RES-JB
    6. 11573
    Prev
    Next
    INDEX
    Explanations

    terms related to maps, locations, and geographic information

    oai_token-act-pair · gpt-3.5-turbo

    words related to geographic and biographical content

    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
     refund
    -0.63
    mut
    -0.61
     Lamb
    -0.61
     fires
    -0.59
     Hew
    -0.57
     Brett
    -0.56
     Branch
    -0.55
     Tun
    -0.55
    san
    -0.55
     Suk
    -0.55
    POSITIVE LOGITS
    ographic
    4.41
    ographical
    3.44
    ographically
    3.39
    ography
    3.16
    ographers
    2.88
    ographies
    2.75
    ographics
    2.67
    ographer
    2.58
    ographs
    2.28
    ograph
    2.27
    Activations Density 0.019%

    No Known Activations