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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 19436
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating immediate actions or reactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "immediately" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    smanship
    -0.71
    itely
    -0.65
    MET
    -0.65
    midt
    -0.65
    glers
    -0.64
    mic
    -0.64
    chance
    -0.64
    à¸
    -0.62
    cius
    -0.62
    doctor
    -0.62
    POSITIVE LOGITS
    aneously
    0.99
     gratification
    0.91
     recognizable
    0.89
     thereafter
    0.86
     upon
    0.85
     regretted
    0.84
     identifiable
    0.79
     preceding
    0.79
    aneous
    0.78
     recogn
    0.77
    Activations Density 0.036%

    No Known Activations