© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 9052
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving review, consideration, purchase, or comment

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to reviews, releases, purchases, and inspections

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

    No Comments

    Negative Logits
    ivan
    -0.62
     Lor
    -0.60
    osphere
    -0.59
     Chevy
    -0.58
     Thom
    -0.57
     nutshell
    -0.57
     Luther
    -0.56
     Mile
    -0.56
     Bellev
    -0.55
     Achilles
    -0.55
    POSITIVE LOGITS
    ulkan
    0.89
    externalActionCode
    0.82
    abwe
    0.79
    aphael
    0.75
     purposes
    0.75
     srfAttach
    0.74
    testing
    0.72
     seekers
    0.72
    holm
    0.72
    bows
    0.70
    Activations Density 0.556%

    No Known Activations