© 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. 9-RES-JB
    11. 7095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sign" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sign" and related concepts

    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
     Remastered
    -0.70
     DRAG
    -0.67
    OSE
    -0.64
    »Ĵ
    -0.62
    ecause
    -0.62
    ETHOD
    -0.61
    IRO
    -0.60
     needle
    -0.59
    ulu
    -0.58
    abama
    -0.58
    POSITIVE LOGITS
    atories
    1.38
    posts
    1.32
    posted
    1.21
    post
    1.19
    atory
    1.18
    ifiers
    1.18
    ificantly
    1.16
    ifier
    1.15
    ifying
    1.10
    atures
    1.07
    Activations Density 0.035%

    No Known Activations