© 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. 2-RES-JB
    11. 21994
    Prev
    Next
    INDEX
    Explanations

    words related to rocks or misspelled variations of "rocks"

    oai_token-act-pair · gpt-3.5-turbo

    references to socks

    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
     shatter
    -0.71
     nep
    -0.67
     hepatitis
    -0.65
    ccording
    -0.64
     gum
    -0.62
    eworks
    -0.62
     denial
    -0.61
    mes
    -0.61
     princip
    -0.60
     responsive
    -0.60
    POSITIVE LOGITS
    ocks
    1.10
    mith
    1.06
    OCK
    0.87
    erk
    0.86
    aults
    0.84
    strap
    0.82
    ocking
    0.81
    bird
    0.80
    DAQ
    0.80
    ocket
    0.76
    Activations Density 0.007%

    No Known Activations