INDEX

Explanations

words indicating the significance or impact of advancements and interventions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 complètement

-0.73

 entièrement

-0.69

 profonda

-0.63

AutoScale

-0.63

 totalement

-0.61

 AssemblyTitle

-0.60

 completamente

-0.59

 efficacement

-0.58

 pleinement

-0.58

 somehow

-0.57

POSITIVE LOGITS

 ligiloj

0.69

 emphasis

0.65

 elseif

0.61

 focus

0.59

 political

0.59

 reliance

0.56

 appreciation

0.56

'][]

0.55

saraba

0.54

UrlResolution

0.53

Activations Density 0.765%

words indicating the significance or impact of advancements and interventions in various contexts

No Comments

No Known Activations