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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 14894
    Prev
    Next
    INDEX
    Explanations

    phrases related to upcoming events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sickness
    -0.77
    ipeg
    -0.69
    aturally
    -0.68
    ilver
    -0.67
     myth
    -0.66
     sqor
    -0.66
     desperation
    -0.64
    achine
    -0.64
    ocre
    -0.63
    emonic
    -0.63
    POSITIVE LOGITS
    fitting
    1.03
    heading
    0.88
     replaced
    0.87
     judged
    0.83
     phased
    0.82
     credited
    0.81
     flown
    0.81
     subjected
    0.80
     honoured
    0.79
     evaluated
    0.79
    Activations Density 0.235%

    No Known Activations