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. 10-RES-JB
    6. 3555
    Prev
    Next
    INDEX
    Explanations

    words related to difficult situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various states or conditions, often related to positions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Egyptians
    -0.71
    Insp
    -0.67
    Trivia
    -0.65
     deeds
    -0.62
    ATURES
    -0.61
     Authorities
    -0.61
     Ukrainians
    -0.61
     graduates
    -0.60
     shores
    -0.59
     icons
    -0.59
    POSITIVE LOGITS
     hurry
    1.28
     predicament
    1.15
     coma
    1.13
     position
    1.11
     precarious
    1.02
     bind
    1.01
     nutshell
    0.98
     trance
    0.96
     situation
    0.94
     compromising
    0.93
    Activations Density 0.072%

    No Known Activations