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. 6-RES-JB
    6. 2443
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocating for or calling for action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rift
    -0.59
     wounding
    -0.58
     backdrop
    -0.58
    laus
    -0.57
    catentry
    -0.56
     Creep
    -0.56
    hill
    -0.56
    etter
    -0.55
     Dough
    -0.52
    etting
    -0.52
    POSITIVE LOGITS
     been
    0.98
     gotten
    0.98
     recourse
    0.91
    gotten
    0.86
     undergone
    0.84
    been
    0.83
     eaten
    0.81
     taken
    0.79
     access
    0.78
     seen
    0.77
    Activations Density 0.114%

    No Known Activations