INDEX

Explanations

numerical data related to rates or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

</th>

-0.64

is

-0.60

</td>

-0.59

↵↵

-0.58

-0.57

</h4>

-0.56

-0.54

-0.53

</

-0.53

POSITIVE LOGITS

 greateſt

0.83

 pleaſure

0.79

 beſt

0.77

 Reſ

0.77

ㅡ

0.76

Eſ

0.76

 Jefus

0.76

 Anſ

0.75

 anſ

0.75

 myſelf

0.74

Activations Density 0.060%

numerical data related to rates or measurements

No Comments

No Known Activations