© 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. 11-RES-JB
    11. 1306
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "reme" or "rem" in them, which may be related to memory or a reference to something in the context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extreme behaviors or ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hath
    -0.68
     sadd
    -0.60
     Hogan
    -0.59
     Typh
    -0.58
     Mehran
    -0.58
     ashore
    -0.57
     Hera
    -0.57
     Labrador
    -0.57
    hare
    -0.57
     Asgard
    -0.56
    POSITIVE LOGITS
    antle
    1.22
    phasis
    1.14
    phas
    1.06
    lins
    1.06
    acists
    1.03
    acist
    0.99
    blers
    0.98
    ichael
    0.94
    nant
    0.94
    estic
    0.94
    Activations Density 0.056%

    No Known Activations