© 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. 23686
    Prev
    Next
    INDEX
    Explanations

    names of individuals with a particular title or description

    oai_token-act-pair · gpt-3.5-turbo

    dash or hyphenated phrases and names

    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
    enei
    -0.63
     infring
    -0.60
    opian
    -0.59
     DSL
    -0.59
    aly
    -0.58
    dal
    -0.54
    hou
    -0.54
     harms
    -0.54
    olyn
    -0.54
     Hearth
    -0.53
    POSITIVE LOGITS
    whose
    1.27
    which
    1.13
    along
    0.98
    who
    0.95
    including
    0.94
     nicknamed
    0.92
    pictured
    0.89
    formerly
    0.89
    ————
    0.88
    currently
    0.87
    Activations Density 0.143%

    No Known Activations