© 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. 10-RES-JB
    11. 2244
    Prev
    Next
    INDEX
    Explanations

    the phrase "needless to say" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orno
    -0.70
    nell
    -0.70
    backs
    -0.66
    arium
    -0.65
    doors
    -0.63
    pins
    -0.62
    terday
    -0.60
    lot
    -0.59
     Reviews
    -0.58
    funding
    -0.58
    POSITIVE LOGITS
     say
    1.07
     SAY
    0.80
     conclude
    0.75
     cliché
    0.75
     understatement
    0.74
     reiterate
    0.74
     mention
    0.73
     note
    0.73
     guessed
    0.68
    lege
    0.67
    Activations Density 0.054%

    No Known Activations