© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    the word "regardless" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the term "regardless" and its variations in various contexts

    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
    ahime
    -0.92
    anz
    -0.75
    raz
    -0.74
    jc
    -0.73
    opter
    -0.69
    ANN
    -0.68
    ARC
    -0.68
    ammad
    -0.66
     syndrome
    -0.65
    ARK
    -0.65
    POSITIVE LOGITS
    etheless
    1.03
    soever
    0.98
    ĸļ
    0.89
    é¾įå¥ij士
    0.85
     irrespective
    0.83
    ¬¼
    0.83
    ħĭ
    0.80
    £ı
    0.79
    theless
    0.79
     materially
    0.76
    Activations Density 0.006%

    No Known Activations