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. 11-RES-JB
    6. 18081
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "profiling"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "prof" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENTS
    -0.64
     shortened
    -0.60
     coupled
    -0.59
    warm
    -0.58
    boarding
    -0.58
    box
    -0.58
     capped
    -0.58
     halfway
    -0.57
     caps
    -0.56
    âĶĢâĶĢâĶĢâĶĢ
    -0.55
    POSITIVE LOGITS
    essor
    1.32
    icient
    1.31
    anity
    1.30
    iciency
    1.26
    ilers
    1.24
    ession
    1.24
    itable
    1.22
    iler
    1.21
    essors
    1.21
    iled
    1.20
    Activations Density 0.020%

    No Known Activations