© 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. 6-RES-JB
    11. 24355
    Prev
    Next
    INDEX
    Explanations

    words or terms related to the name "arr."

    oai_token-act-pair · gpt-3.5-turbo

    the word 'arr' in various contexts, indicating a thematic focus on the word itself

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.87
     Pixie
    -0.79
    ku
    -0.75
    dayName
    -0.74
    lasses
    -0.72
    chal
    -0.65
    olithic
    -0.65
    lla
    -0.65
    utral
    -0.65
    lucent
    -0.63
    POSITIVE LOGITS
    agher
    1.05
    anged
    0.94
    anging
    0.93
    abilia
    0.93
    issa
    0.91
    andom
    0.90
    INGTON
    0.89
    anger
    0.88
    agh
    0.87
    ange
    0.86
    Activations Density 0.023%

    No Known Activations