© 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. 24146
    Prev
    Next
    INDEX
    Explanations

    words related to "rav" or potentially relating to themes such as sacrifice, politics, and physical checks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Rav" and variations associated with it

    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
    lder
    -0.68
     Forth
    -0.67
     Catalyst
    -0.65
    ça
    -0.64
    ħĭ
    -0.63
    onomy
    -0.62
     Coke
    -0.62
    print
    -0.62
     Byrne
    -0.61
     testify
    -0.59
    POSITIVE LOGITS
    itational
    1.07
    rav
    0.91
    ski
    0.91
    atar
    0.87
    iew
    0.87
    oslav
    0.87
    onite
    0.86
    aria
    0.86
    itz
    0.86
    aband
    0.82
    Activations Density 0.007%

    No Known Activations