© 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. 6-RES-JB
    11. 11950
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploiting resources or opportunities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "tapping into" various ideas or movements

    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
    mos
    -0.86
    stad
    -0.76
    heading
    -0.74
    kees
    -0.73
    cats
    -0.70
    ĺ
    -0.69
    starter
    -0.69
    Ĥ¬
    -0.69
    cot
    -0.68
    bender
    -0.67
    POSITIVE LOGITS
     vein
    0.82
     intu
    0.81
     energies
    0.79
     recess
    0.79
    osterone
    0.77
     impulses
    0.75
     stereotypes
    0.74
     subconscious
    0.73
     loopholes
    0.70
     imag
    0.69
    Activations Density 0.112%

    No Known Activations