INDEX

Explanations

references to historical events, entities related to warfare, and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

adpleegd

-0.96

 فريبيس

-0.92

NUMX

-0.91

تقاوى

-0.85

 puissiez

-0.78

 GenerationType

-0.77

EDEFAULT

-0.76

webElementXpaths

-0.76

.",

-0.76

bbene

-0.75

POSITIVE LOGITS

<eos>

0.95

↵↵

0.87

0.80

↵

0.79

0.64

vs

0.58

is

0.58

0.56

↵↵↵

0.56

0.54

Activations Density 2.473%

references to historical events, entities related to warfare, and programming concepts

No Comments

No Known Activations