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

    Neuronpedia

    Jacobian LensNEW
    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. 14770
    Prev
    Next
    INDEX
    Explanations

    phrases related to moving or transitioning from one state to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "off" 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
    amount
    -0.67
    gers
    -0.63
    Enlarge
    -0.61
    ¿
    -0.61
    ļéĨĴ
    -0.61
    MX
    -0.60
    berus
    -0.60
    ¶ħ
    -0.59
     disproportionate
    -0.59
    MpServer
    -0.59
    POSITIVE LOGITS
    loaded
    1.07
    site
    1.05
    screen
    1.05
    stage
    1.01
    eatures
    0.96
    loading
    0.92
    shoot
    0.92
    sites
    0.86
     cliffs
    0.85
     leash
    0.82
    Activations Density 0.047%

    No Known Activations