INDEX

Explanations

phrases that express making things easier or better

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-0.94

 houſe

-0.94

Efq

-0.92

 whoſe

-0.92

 pleaſure

-0.91

 utafitiHapana

-0.88

 ſhe

-0.86

 Majefty

-0.86

 againſt

-0.86

 raiſ

-0.85

POSITIVE LOGITS

 make

1.09

 Make

1.00

 makes

0.94

 MAKE

0.92

make

0.92

Make

0.91

 made

0.91

Makes

0.84

 MAKES

0.81

 making

0.81

Activations Density 0.153%

phrases that express making things easier or better

No Comments

No Known Activations