© 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. 1-RES-JB
    11. 3542
    Prev
    Next
    INDEX
    Explanations

    Unique IDs, especially those related to devices or authentication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of unique identifiers and references to video-related terms

    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
     advant
    -0.73
    neau
    -0.69
     Leban
    -0.69
    uliffe
    -0.69
     behav
    -0.66
    OUP
    -0.65
    ebus
    -0.63
     flap
    -0.63
     antioxid
    -0.62
     Koreans
    -0.62
    POSITIVE LOGITS
    irection
    1.14
    itor
    1.00
    iaries
    1.00
    gets
    0.96
    ocument
    0.94
    ysis
    0.94
    pid
    0.94
    eways
    0.93
    aho
    0.93
    der
    0.92
    Activations Density 0.016%

    No Known Activations