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. 8-RES-JB
    6. 12075
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "Conn" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Conn" or its variations, likely indicating references to Connecticut or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Defenders
    -0.70
     english
    -0.67
     Savior
    -0.61
     NIC
    -0.59
     chalk
    -0.58
     simul
    -0.58
     parap
    -0.57
     parking
    -0.57
    footed
    -0.56
    mining
    -0.56
    POSITIVE LOGITS
    olly
    1.06
    ors
    1.04
    elly
    1.00
    oms
    1.00
    oming
    0.93
    enger
    0.93
    orm
    0.91
    orship
    0.88
    ored
    0.86
    adal
    0.83
    Activations Density 0.072%

    No Known Activations