INDEX

Explanations

phrases about malfunctioning or non-working items

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

IndentedString

-0.87

 GenerationType

-0.84

CPtr

-0.73

 Roskov

-0.73

 незавершена

-0.70

adaptiveStyles

-0.70

tableFuture

-0.69

+#+#

-0.68

ьаж

-0.68

CloseOperation

-0.68

POSITIVE LOGITS

 properly

1.55

properly

1.25

 Properly

1.19

 adequately

1.19

 proper

1.14

 correctly

1.12

 PROPER

1.06

Proper

1.04

 correctement

1.03

 adequate

0.99

Activations Density 0.556%

phrases about malfunctioning or non-working items

No Comments

No Known Activations