© 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. 10-RES-JB
    11. 2700
    Prev
    Next
    INDEX
    Explanations

    occurrences of text encoding characters

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to perceptions and interpretations, particularly in the context of societal issues

    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
     misunder
    -0.71
     JPEG
    -0.70
     decomp
    -0.64
     unofficial
    -0.63
     advis
    -0.62
     Mobil
    -0.62
     cellphone
    -0.62
     unidentified
    -0.61
     conspicuous
    -0.61
     retirees
    -0.61
    POSITIVE LOGITS
    s
    1.32
    tion
    1.05
    _.
    1.04
    til
    1.03
    tis
    1.00
    sit
    0.99
    sis
    0.98
    ski
    0.96
    swer
    0.95
    cause
    0.95
    Activations Density 0.223%

    No Known Activations