© 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. 18207
    Prev
    Next
    INDEX
    Explanations

    phrases indicating pointed out or highlighted information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating observation or awareness

    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
    prus
    -0.68
    estern
    -0.68
    izens
    -0.61
    rig
    -0.61
    jing
    -0.61
    ococ
    -0.61
    rency
    -0.59
    addons
    -0.59
    jug
    -0.59
    rang
    -0.58
    POSITIVE LOGITS
    ,.
    0.91
     (),
    0.86
    ,
    0.83
    ,,
    0.80
    .,
    0.76
     wont
    0.70
    ,-
    0.69
    âĶĢ
    0.68
    terday
    0.67
    (),
    0.66
    Activations Density 0.078%

    No Known Activations