© 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. 7-RES-JB
    11. 21161
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thing."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of "thing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    avorite
    -0.75
     anonymity
    -0.69
     crest
    -0.66
    ãĥ©ãĥ³
    -0.66
    cul
    -0.64
    ettings
    -0.64
    atching
    -0.63
    ramid
    -0.62
     Telecommunications
    -0.62
     simul
    -0.62
    POSITIVE LOGITS
    iverse
    1.25
     happening
    0.84
     happ
    0.83
     Valiant
    0.82
     happened
    0.82
    ional
    0.79
    ion
    0.76
    hered
    0.75
    ie
    0.74
    y
    0.72
    Activations Density 0.039%

    No Known Activations