INDEX

Explanations

phrases indicating a time frame or interval

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 noastre

-0.60

LayoutStyle

-0.58

 suivantes

-0.58

 Lijst

-0.57

 extérieures

-0.54

 AssemblyCulture

-0.54

 LoggerFactory

-0.54

 NIOS

-0.52

RegressionTest

-0.52

 fogo

-0.51

POSITIVE LOGITS

 Within

0.99

within

0.95

 within

0.93

Within

0.92

 WITHIN

0.85

]<=

0.77

 minutes

0.75

 reason

0.74

 reach

0.72

 seconds

0.69

Activations Density 0.087%

phrases indicating a time frame or interval

No Comments

No Known Activations