© 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. 7-RES-JB
    11. 17185
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and taking action for a cause or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging collective action and responsibility for positive social change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Originally
    -0.73
    note
    -0.66
    famous
    -0.64
    ocular
    -0.62
     Radar
    -0.60
    DragonMagazine
    -0.60
     Stern
    -0.59
     Carlo
    -0.58
     puzzled
    -0.58
     Newsp
    -0.58
    POSITIVE LOGITS
     ourselves
    0.88
     future
    0.80
     meaningful
    0.79
     mutually
    0.77
     sustainable
    0.77
     collectively
    0.75
     tomorrow
    0.75
     someday
    0.75
     accomplish
    0.74
     prosperity
    0.74
    Activations Density 0.510%

    No Known Activations