© 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. 4838
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an addition or enhancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate contributions or increments to a situation or context

    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
     Laws
    -0.65
     writ
    -0.61
     Choose
    -0.58
     mailing
    -0.57
     Seymour
    -0.56
    bred
    -0.56
     mishand
    -0.55
     Inher
    -0.54
     Associated
    -0.54
    kay
    -0.54
    POSITIVE LOGITS
     insult
    0.95
    ictions
    0.91
     impetus
    0.88
     tremend
    0.84
    ressing
    0.84
    ictive
    0.83
    itionally
    0.83
    endum
    0.82
    iction
    0.81
     urgency
    0.81
    Activations Density 0.077%

    No Known Activations