© 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. 1-RES-JB
    11. 20969
    Prev
    Next
    INDEX
    Explanations

    declarations of confirmation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "confirm."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.82
    DIR
    -0.72
    dro
    -0.70
    @#&
    -0.70
    tur
    -0.68
     ILCS
    -0.66
     sidx
    -0.66
    ï¸
    -0.66
    pen
    -0.64
    tra
    -0.64
    POSITIVE LOGITS
    irmation
    1.25
     confirm
    1.16
     confirmation
    1.03
    irms
    1.01
     confirms
    1.01
     confirming
    0.99
    irmed
    0.92
     confirmed
    0.92
    ifications
    0.88
    esses
    0.88
    Activations Density 0.010%

    No Known Activations