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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14470
    Prev
    Next
    INDEX
    Explanations

    references to different levels in a hierarchical system

    oai_token-act-pair · gpt-3.5-turbo

    references to levels in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.84
    oute
    -0.81
    rontal
    -0.76
    女
    -0.73
    uter
    -0.67
    ILLE
    -0.67
     Sidd
    -0.66
     Leilan
    -0.66
     vot
    -0.66
    ãĥĨãĤ£
    -0.64
    POSITIVE LOGITS
    level
    0.78
     attainment
    0.71
     advancement
    0.66
    ottage
    0.65
     crossings
    0.64
     attained
    0.64
     certific
    0.63
    casting
    0.63
    ership
    0.63
    Level
    0.62
    Activations Density 0.026%

    No Known Activations