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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 20581
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgent actions or responses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urgency and chaotic activity

    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
    hetical
    -0.79
    negative
    -0.68
    oral
    -0.64
    ī
    -0.63
    paying
    -0.62
    mentioned
    -0.60
    rica
    -0.60
     concess
    -0.60
    ihar
    -0.60
    Ĵ
    -0.59
    POSITIVE LOGITS
     scramble
    1.18
     scram
    1.02
     scrambling
    0.95
     scrambled
    0.89
    berry
    0.79
     frantically
    0.74
     eggs
    0.72
     furiously
    0.72
    DAQ
    0.71
    iness
    0.70
    Activations Density 0.037%

    No Known Activations