© 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. 8-RES-JB
    11. 24048
    Prev
    Next
    INDEX
    Explanations

    instances of the word "replacement"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "replacement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -1.00
    jah
    -0.84
    UGE
    -0.75
    eta
    -0.72
    emi
    -0.67
    kers
    -0.67
    aceae
    -0.67
    ographed
    -0.66
    omen
    -0.65
    rica
    -0.65
    POSITIVE LOGITS
    mentation
    0.79
    mented
    0.71
    ãĥ¤
    0.70
    aneous
    0.70
     thereof
    0.67
     limbs
    0.66
    ptive
    0.65
    utions
    0.64
    atives
    0.63
     replacements
    0.63
    Activations Density 0.033%

    No Known Activations