© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 16823
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named "Bec" with varying numerical strengths

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Bec" or variations of it

    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
     belts
    -0.72
    PAC
    -0.70
     belt
    -0.70
    tsky
    -0.67
    è¦ļéĨĴ
    -0.66
     Nadu
    -0.66
    Reviewer
    -0.63
     Siberian
    -0.63
    PLIED
    -0.62
     prefrontal
    -0.60
    POSITIVE LOGITS
    oming
    1.43
    omes
    1.19
    uity
    1.04
    zek
    1.00
    ues
    0.90
    uous
    0.88
    ome
    0.87
    ued
    0.86
    OME
    0.84
    ilic
    0.83
    Activations Density 0.033%

    No Known Activations