Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9363
    Prev
    Next
    INDEX
    Explanations

    places and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with specific cultural or ethnic identities

    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
     analytics
    -0.81
     situational
    -0.80
     affordability
    -0.75
     scoreboard
    -0.71
     sustainability
    -0.70
     robotics
    -0.70
     shaky
    -0.70
     predetermined
    -0.67
     firewall
    -0.66
     cybersecurity
    -0.66
    POSITIVE LOGITS
    aceae
    1.19
    idae
    1.09
    nian
    1.08
    va
    0.98
    zes
    0.97
    onian
    0.97
    opsis
    0.96
    heit
    0.96
    ux
    0.95
    aux
    0.95
    Activations Density 0.442%

    No Known Activations