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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 7590
    Prev
    Next
    INDEX
    Explanations

    titles or headings related to software, organizations, or specific topics

    oai_token-act-pair · gpt-3.5-turbo

    titles or phrases indicating instructional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disarm
    -0.76
     aven
    -0.74
     fierce
    -0.71
     pity
    -0.70
     disg
    -0.69
     drowned
    -0.69
     unrel
    -0.68
     incap
    -0.67
     wretched
    -0.67
    ifully
    -0.66
    POSITIVE LOGITS
     =================
    1.09
    ¶
    1.05
     Quote
    1.02
     Programs
    1.01
    ?:
    1.00
     Prices
    1.00
     Allows
    0.98
     Shows
    0.97
     Extensions
    0.97
     Values
    0.97
    Activations Density 0.687%

    No Known Activations