© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 13617
    Prev
    Next
    INDEX
    Explanations

    phrases related to information dissemination or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating familiarity or awareness about ongoing topics or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.65
    grades
    -0.61
     prolong
    -0.59
     sacrific
    -0.58
     openness
    -0.57
     preserves
    -0.56
     stunts
    -0.56
     differentiation
    -0.55
     downgrade
    -0.55
     stabilization
    -0.55
    POSITIVE LOGITS
     guessed
    1.14
     noticed
    1.13
     familiar
    1.12
     heard
    1.06
     know
    0.95
     watched
    0.93
    know
    0.92
     acquainted
    0.91
     remember
    0.88
     already
    0.88
    Activations Density 0.249%

    No Known Activations