INDEX

Explanations

sections that indicate a positive or commendatory tone regarding experiences or evaluations

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

 Atiku

-1.08

 Kendal

-1.07

 Trafalgar

-1.02

IsMutable

-0.98

 CreateTagHelper

-0.97

 Lordships

-0.97

 Freya

-0.96

ificance

-0.96

FAO

-0.95

ytale

-0.95

POSITIVE LOGITS

—

1.42

————————————————

1.09

1.01

==

0.97

———

0.93

————————

0.88

cbd

0.86

«

0.84

————

0.82

ly

0.80

Activations Density 0.162%

sections that indicate a positive or commendatory tone regarding experiences or evaluations

No Comments

No Known Activations