INDEX

Explanations

phrases that indicate unexpected changes or events

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

 partea

-0.62

 présidentielle

-0.59

pyrene

-0.59

Poo

-0.59

 marito

-0.59

 ritratto

-0.55

 estoppel

-0.55

@[

-0.55

 setShow

-0.54

 frutto

-0.54

POSITIVE LOGITS

 suddenly

1.66

 sudden

1.63

Sudden

1.52

 Sudden

1.52

 Suddenly

1.43

Suddenly

1.42

suddenly

1.40

 soudain

1.25

突然

1.15

 abrupt

1.13

Activations Density 0.113%

phrases that indicate unexpected changes or events

No Comments

No Known Activations