INDEX

Explanations

references to time-related concepts, particularly regarding short-term and long-term perspectives or outcomes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 שוליים

-0.79

interopRequire

-0.75

NameInMap

-0.74

migrationBuilder

-0.73

#+#

-0.70

IGraphics

-0.64

تقاوى

-0.64

IMPORTED

-0.61

principalColumn

-0.60

 <=",

-0.60

POSITIVE LOGITS

 term

1.25

term

1.06

run

1.02

run

0.91

 TERM

0.80

 Term

0.79

Term

0.78

Run

0.76

 midterm

0.72

 medium

0.72

Activations Density 0.220%

references to time-related concepts, particularly regarding short-term and long-term perspectives or outcomes

No Comments

No Known Activations