© 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. 0-RES-JB
    11. 20449
    Prev
    Next
    INDEX
    Explanations

    words related to high intensity or significance

    oai_token-act-pair · gpt-3.5-turbo

    the word "high" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ART
    -0.68
     exploitation
    -0.65
     promoted
    -0.64
     assignments
    -0.64
     fusion
    -0.64
     bubble
    -0.63
     bubbles
    -0.63
     destruction
    -0.63
     molten
    -0.63
     replication
    -0.61
    POSITIVE LOGITS
    igh
    4.59
    ighed
    2.32
    IGH
    2.04
    ights
    1.43
    ighter
    1.38
    ignt
    1.20
    agh
    1.19
    IGHT
    1.18
    ight
    1.18
    ighth
    1.16
    Activations Density 0.010%

    No Known Activations