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. 10-RES-JB
    6. 11501
    Prev
    Next
    INDEX
    Explanations

    mentions of ongoing or anticipated events and activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to filmmaking and its production processes

    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
    —"
    -1.02
     ÂŃ
    -0.92
    Newsletter
    -0.88
    ___
    -0.84
    "—
    -0.81
     ..."
    -0.81
     Photograph
    -0.78
    âĢ¢âĢ¢
    -0.75
    Enlarge
    -0.73
     â̦"
    -0.72
    POSITIVE LOGITS
     utilizing
    1.23
     utilized
    1.15
     utilizes
    1.02
     utilize
    0.99
     amongst
    0.98
     alot
    0.96
     whilst
    0.96
     showcased
    0.89
     unfortunately
    0.88
     Whilst
    0.85
    Activations Density 1.630%

    No Known Activations