© 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. 7-RES-JB
    11. 9621
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names specifically related to entities or individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outwe
    -0.65
     beforehand
    -0.60
    ĪĴ
    -0.59
     behav
    -0.57
     disadvant
    -0.56
     Azerb
    -0.56
    userc
    -0.56
     behavi
    -0.54
     undermin
    -0.53
     prevailed
    -0.52
    POSITIVE LOGITS
    olin
    0.50
     Norwich
    0.48
     Belfast
    0.48
     âĢº
    0.47
     Historic
    0.47
     Patreon
    0.46
     ..........
    0.45
     Crossref
    0.45
    veland
    0.45
    canon
    0.43
    Activations Density 1.298%

    No Known Activations