© 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. 9-RES-JB
    11. 13108
    Prev
    Next
    INDEX
    Explanations

    specific nouns or noun phrases related to various scenarios or circumstances, such as job titles, medical conditions, relationships, and actions

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to roles or relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.93
    ntil
    -0.81
    soDeliveryDate
    -0.78
    allery
    -0.71
    udeb
    -0.67
    Dub
    -0.66
    soType
    -0.66
    "]=>
    -0.65
    ranging
    -0.63
    TPPStreamerBot
    -0.62
    POSITIVE LOGITS
     enters
    1.23
     fails
    1.22
     receives
    1.18
     refuses
    1.18
     exceeds
    1.18
     chooses
    1.16
     succeeds
    1.15
     engages
    1.15
     wants
    1.14
     meets
    1.14
    Activations Density 0.349%

    No Known Activations