INDEX

Explanations

variations of the word "pool" in different contexts

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

 متعلقه

-1.05

ündigen

-0.75

 johnny

-0.74

 Bellingham

-0.71

 condamné

-0.71

 réfugi

-0.70

 '\\;'

-0.70

__(/*!

-0.70

 Westwood

-0.69

 Johanna

-0.68

POSITIVE LOGITS

 pool

3.00

 Pool

2.83

 pools

2.79

pool

2.53

 POOL

2.52

 Pools

2.48

Pool

2.47

pools

2.33

Pools

2.25

POOL

2.07

Activations Density 0.032%

variations of the word "pool" in different contexts

No Comments

No Known Activations