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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 578
    Prev
    Next
    INDEX
    Explanations

    names mentioned, presumably with a special focus on usernames or handles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and brands within the content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ske
    -0.86
     handic
    -0.85
     SAP
    -0.82
     Carib
    -0.81
     Haz
    -0.80
     Emb
    -0.78
     Tib
    -0.77
     HRC
    -0.76
     medic
    -0.75
     Scouting
    -0.74
    POSITIVE LOGITS
    ons
    1.52
    oni
    1.44
    onian
    1.44
    ON
    1.42
    on
    1.41
    onal
    1.37
    onia
    1.34
    onic
    1.33
    ony
    1.31
    onis
    1.30
    Activations Density 0.192%

    No Known Activations