INDEX

Explanations

terms related to immune response and activity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.94

CloseOperation

-0.72

SourceChecksum

-0.69

ymce

-0.69

Wex

-0.69

extAlignment

-0.68

AsUp

-0.68

 viewDidLoad

-0.65

floxacin

-0.65

sidemargin

-0.65

POSITIVE LOGITS

 immune

1.85

 Immune

1.74

 immunity

1.70

immune

1.68

Immune

1.61

 immun

1.57

 Immunity

1.47

immunity

1.45

 inmun

1.41

immun

1.40

Activations Density 0.164%

terms related to immune response and activity

No Comments

No Known Activations