© 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. 2-RES-JB
    11. 11060
    Prev
    Next
    INDEX
    Explanations

    keywords related to tech jargon and coding, specifically centered around terms related to web security and operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "snoop" and "swoop."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.69
     circumst
    -0.69
    STD
    -0.65
     circumstance
    -0.62
     Pwr
    -0.61
    nexus
    -0.60
    imen
    -0.60
    penter
    -0.59
    pace
    -0.59
     Proposition
    -0.59
    POSITIVE LOGITS
    oop
    1.30
    opa
    0.85
    dropping
    0.82
    arser
    0.81
    ishly
    0.80
    oops
    0.80
    onte
    0.79
    eful
    0.78
    ood
    0.78
    efully
    0.78
    Activations Density 0.008%

    No Known Activations