© 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. 1-RES-JB
    11. 16423
    Prev
    Next
    INDEX
    Explanations

    phrases or sequences that are represented by special characters, such as 'âĢ¦'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the "âĢ¦" character or symbol used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icum
    -0.84
     purse
    -0.77
    pper
    -0.77
     bod
    -0.73
    ppings
    -0.73
    onds
    -0.72
    ppers
    -0.72
     womb
    -0.72
     reper
    -0.71
    ilion
    -0.69
    POSITIVE LOGITS
    âĢ¦âĢ¦âĢ¦âĢ¦
    1.17
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    1.13
    BUT
    0.84
     âĢ¦
    0.80
     Written
    0.80
    Marginal
    0.80
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.79
    .?
    0.77
    ..
    0.77
     ,"
    0.77
    Activations Density 0.010%

    No Known Activations