© 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. 2-RES-JB
    11. 4240
    Prev
    Next
    INDEX
    Explanations

    phrases related to common clichés

    oai_token-act-pair · gpt-3.5-turbo

    expressions of clichéd ideas or phrases

    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
    ŃĶ
    -0.82
    uppet
    -0.77
    ĸļ
    -0.77
    andum
    -0.73
    umerable
    -0.72
    ²¾
    -0.69
     Donn
    -0.67
    arthed
    -0.66
    abase
    -0.66
    hyde
    -0.66
    POSITIVE LOGITS
    ded
    0.94
    spr
    0.88
    s
    0.87
    d
    0.83
    ontent
    0.80
    forward
    0.80
    ding
    0.78
    ties
    0.76
    dh
    0.76
    dt
    0.73
    Activations Density 0.024%

    No Known Activations