INDEX

Explanations

references to relationships and comparisons among entities or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 nakalista

-0.81

StructEnd

-0.72

 versehen

-0.66

IonicModule

-0.66

rawDesc

-0.64

 Walkover

-0.62



-0.61

 Audiodateien

-0.60

CardModule

-0.58

 surla

-0.56

POSITIVE LOGITS

 with

3.52

with

2.46

 avec

2.45

 dengan

2.21

 WITH

2.08

 với

2.03

 With

1.95

With

1.94

avec

1.73

 עם

1.63

Activations Density 4.368%

references to relationships and comparisons among entities or ideas

No Comments

No Known Activations