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. 12-RES-JB
    6. 15257
    Prev
    Next
    INDEX
    Explanations

    locations or places within a country

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    locations and geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ£
    -0.89
    Reviewer
    -0.82
    IUM
    -0.67
     toget
    -0.65
    DEN
    -0.65
     assures
    -0.64
    anamo
    -0.63
    ngth
    -0.63
    esome
    -0.63
    ylum
    -0.62
    POSITIVE LOGITS
     southwestern
    1.19
     northwestern
    1.17
     northeastern
    1.16
     northwest
    1.12
     southwest
    1.12
     southeastern
    1.11
     southern
    1.07
     northern
    1.07
     northeast
    1.05
     western
    1.04
    Activations Density 0.156%

    No Known Activations