© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9877
    Prev
    Next
    INDEX
    Explanations

    social media handles and website URLs

    oai_token-act-pair · gpt-3.5-turbo

    social media interactions and popular hashtags

    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
     Editorial
    -0.87
     Parish
    -0.86
     Tier
    -0.86
     Sachs
    -0.86
     Ninth
    -0.85
     Levy
    -0.83
     Bowen
    -0.82
     Socket
    -0.81
     Act
    -0.80
     Guang
    -0.80
    POSITIVE LOGITS
    oft
    1.51
    pod
    1.44
    kid
    1.42
    music
    1.40
    beaut
    1.39
    circle
    1.38
    christ
    1.38
    podcast
    1.38
    facts
    1.38
    politics
    1.37
    Activations Density 0.193%

    No Known Activations