Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3133
    Prev
    Next
    INDEX
    Explanations

    imagination or hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    hypothetical scenarios or thought experiments

    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
    taboola
    -0.88
    */(
    -0.73
    displayText
    -0.70
    ã쮿
    -0.69
     recess
    -0.67
    ãģĨ
    -0.65
    uld
    -0.65
    ][/
    -0.62
    Ô
    -0.62
    IAL
    -0.62
    POSITIVE LOGITS
     hypot
    0.86
     Seymour
    0.81
     suppose
    0.71
     imagine
    0.70
     Bezos
    0.63
     Nex
    0.63
    amaz
    0.62
    andum
    0.62
     Suppose
    0.61
    adays
    0.60
    Activations Density 0.053%

    No Known Activations