© 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. 15183
    Prev
    Next
    INDEX
    Explanations

    phrases related to confirming or asserting something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to affirmation and support

    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
    devices
    -0.78
    OTOS
    -0.76
    DragonMagazine
    -0.76
    NetMessage
    -0.75
     Horses
    -0.73
    sites
    -0.73
    Ox
    -0.71
    pmwiki
    -0.69
    fare
    -0.69
    FIX
    -0.68
    POSITIVE LOGITS
     affirm
    1.29
    irming
    1.25
    irmed
    1.11
    irmation
    1.11
     affirmation
    1.10
    atively
    1.03
    irm
    0.97
     unequivocally
    0.89
    irms
    0.87
    uctor
    0.81
    Activations Density 0.013%

    No Known Activations