INDEX

Explanations

references to films and their awards

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

HOC

-0.47

 concl

-0.45

 corred

-0.45

//

-0.44

 load

-0.44

 suon

-0.43

Load

-0.42

Statics

-0.42

 Load

-0.42

 poveznice

-0.42

POSITIVE LOGITS

 awards

1.15

 award

1.10

 Awards

1.08

Awards

1.05

 Oscars

1.03

 Award

1.01

 nominations

1.01

awards

0.99

 awarding

0.98

########.

0.97

Activations Density 0.131%

references to films and their awards

No Comments

No Known Activations