© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 24063
    Prev
    Next
    INDEX
    Explanations

    similes describing resemblance to specific objects or environments

    oai_token-act-pair · gpt-3.5-turbo

    comparisons using the word 'like'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifi
    -0.79
    icians
    -0.73
    atel
    -0.73
    omics
    -0.71
    achus
    -0.70
    alf
    -0.70
    restling
    -0.69
    ilitary
    -0.69
    bell
    -0.69
    yna
    -0.69
    POSITIVE LOGITS
    lihood
    2.13
     tendencies
    1.04
     qualities
    0.97
     structures
    0.94
    liest
    0.92
     behaviors
    0.91
     structure
    0.90
     behavior
    0.89
    liness
    0.88
     substance
    0.88
    Activations Density 0.035%

    No Known Activations