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. 1-RES-JB
    6. 14912
    Prev
    Next
    INDEX
    Explanations

    words related to the verb "to impale" or similar concepts of piercing or penetrating

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and participles related to actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pron
    -0.66
     FEC
    -0.65
    flush
    -0.64
    cci
    -0.62
    feat
    -0.61
     CPC
    -0.60
    bler
    -0.60
    Premium
    -0.60
    writer
    -0.59
     donor
    -0.59
    POSITIVE LOGITS
    aled
    1.03
    aling
    0.97
    ashtra
    0.89
    gorith
    0.85
    axy
    0.81
    gorithm
    0.74
    phabet
    0.74
    amy
    0.72
    rawdownloadcloneembedreportprint
    0.72
    terness
    0.71
    Activations Density 0.006%

    No Known Activations