© 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. 6-RES-JB
    11. 7807
    Prev
    Next
    INDEX
    Explanations

    the letters 't' with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    negations and the word "not."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reloaded
    -0.72
     Passenger
    -0.65
    ħĭ
    -0.65
     descent
    -0.64
     Penguin
    -0.61
     Pike
    -0.60
     Seah
    -0.59
     behavi
    -0.59
     Palestin
    -0.59
    çĦ
    -0.59
    POSITIVE LOGITS
    ween
    1.01
    reprene
    0.93
    unes
    0.92
    une
    0.91
    urb
    0.82
    urtles
    0.82
    weet
    0.82
    aper
    0.81
    ruly
    0.80
    UNE
    0.78
    Activations Density 0.113%

    No Known Activations