© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2153
    Prev
    Next
    INDEX
    Explanations

    names or words with the suffix '-z'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'z'

    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
    Reviewer
    -0.73
     behavi
    -0.71
     arming
    -0.70
     Palestin
    -0.69
    uctor
    -0.68
     achie
    -0.65
    naissance
    -0.65
     totality
    -0.65
     temptation
    -0.65
     compe
    -0.64
    POSITIVE LOGITS
    ombie
    1.54
    ombies
    1.36
    oning
    1.08
    enegger
    1.07
    ijn
    1.06
    ebra
    1.05
    oom
    1.04
    umi
    1.01
    iah
    1.01
    eta
    1.01
    Activations Density 0.024%

    No Known Activations