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. 7-RES-JB
    6. 9147
    Prev
    Next
    INDEX
    Explanations

    locations and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of places and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¦
    -0.74
    VALUE
    -0.73
    requ
    -0.72
    akable
    -0.71
    ãĥĻ
    -0.71
    arov
    -0.70
    ī
    -0.69
    agonists
    -0.68
     destro
    -0.67
     sacrific
    -0.67
    POSITIVE LOGITS
     County
    1.34
     Borough
    1.26
     Township
    1.20
     Hills
    1.11
     Heights
    1.10
     resident
    1.10
     Peninsula
    1.10
     Valley
    1.09
     Avenue
    1.08
     residents
    1.07
    Activations Density 0.483%

    No Known Activations