© 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
    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. 21531
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Back in" followed by a year

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or references to a specific time period in the past

    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
    irs
    -0.69
     therein
    -0.65
    WER
    -0.64
    lain
    -0.64
    isitions
    -0.63
    ĺħ
    -0.63
    alogy
    -0.63
    bsp
    -0.63
     importantly
    -0.62
    obar
    -0.61
    POSITIVE LOGITS
     2004
    1.05
     2007
    1.05
     2006
    1.04
     2005
    1.02
     2003
    1.01
     2008
    1.01
     2009
    1.01
     2002
    1.00
     1990
    0.99
     1986
    0.99
    Activations Density 0.052%

    No Known Activations