© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 8164
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions and intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ivid" or variations of it, which may relate to themes of life or energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.76
    çĦ
    -0.67
     clipboard
    -0.66
    conservancy
    -0.65
    piece
    -0.65
     permitting
    -0.65
    queue
    -0.65
     DRAG
    -0.64
    errors
    -0.64
    repair
    -0.62
    POSITIVE LOGITS
    ivid
    1.13
    itri
    1.05
    atives
    0.85
    itives
    0.84
    acion
    0.84
    ition
    0.81
    escent
    0.81
    ados
    0.79
    itional
    0.78
     Hots
    0.75
    Activations Density 0.013%

    No Known Activations