INDEX

Explanations

terms related to evidence and data within 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 @ 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

 ComVisible

-0.71

#+#

-0.62

Rhestr

-0.61

SourceChecksum

-0.57

NKC

-0.55

elfde

-0.54

 igång

-0.53

paravant

-0.51

 FBref

-0.51

POSITIVE LOGITS

new

1.47

 nueva

1.22

new

1.20

新的

1.20

 nuevas

1.18

 nuevos

1.17

 baru

1.16

新

1.13

 nuevo

1.12

ใหม่

1.09

Activations Density 0.337%

terms related to evidence and data within various contexts

No Comments

No Known Activations