© 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. 15849
    Prev
    Next
    INDEX
    Explanations

    quotations in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the use of commas and conversational phrases in reported speech

    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
    oros
    -0.65
    ensible
    -0.63
    atible
    -0.62
    imately
    -0.61
    rait
    -0.59
    elong
    -0.59
    asted
    -0.59
     Covenant
    -0.58
    ileged
    -0.58
    oin
    -0.57
    POSITIVE LOGITS
     referring
    1.37
     adding
    1.34
     noting
    1.20
     citing
    1.15
     referencing
    1.15
     echoing
    1.14
     recalling
    1.11
     stressing
    1.09
     quoting
    1.07
     emphasizing
    1.06
    Activations Density 0.128%

    No Known Activations