© 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 EvalsExportsinterp-engineNEWAPI 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. 11445
    Prev
    Next
    INDEX
    Explanations

    words connected with associations or relationships between concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to associations or correlations within 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
    OUT
    -0.74
    tein
    -0.71
    intend
    -0.70
    athom
    -0.69
    pan
    -0.69
     helicop
    -0.67
    nl
    -0.67
    umblr
    -0.66
    ciples
    -0.66
    aneers
    -0.65
    POSITIVE LOGITS
    atively
    0.89
     with
    0.88
    ively
    0.82
    ativity
    0.81
    ative
    0.81
     thereto
    0.80
     wi
    0.72
     With
    0.68
    with
    0.68
    ational
    0.67
    Activations Density 0.050%

    No Known Activations