INDEX

Explanations

references to original versions or replicas of objects and their comparisons

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__":

-0.82

 שוליים

-0.79

DebuggerNonUser

-0.78

WriteAttribute

-0.78

complexContent

-0.78

ंदीखरीदारी

-0.77

 estimés

-0.76

tagHelperRunner

-0.76

ChildIndex

-0.74

ContentAsync

-0.73

POSITIVE LOGITS

 original

0.81

original

0.72

 originais

0.65

 originals

0.65

 Original

0.63

Original

0.63

 originales

0.61

 originale

0.59

 ORIGINAL

0.58

 оригинал

0.58

Activations Density 0.620%

references to original versions or replicas of objects and their comparisons

No Comments

No Known Activations