INDEX

Explanations

instances of the word "thought" and its related forms, focusing on the quality and depth of ideas expressed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.82

er

-0.81

ers

-0.71

 daly

-0.71

-0.70

 Daly

-0.70

rý

-0.69

legungen

-0.69

lgica

-0.69

drücken

-0.68

POSITIVE LOGITS

 Thought

1.74

thought

1.69

 THOUGHT

1.66

Thought

1.64

 thought

1.61

thoughts

1.26

 thoughts

1.21

 Thoughts

1.09

Thoughts

1.00

 THOUGHTS

0.99

Activations Density 0.104%

instances of the word "thought" and its related forms, focusing on the quality and depth of ideas expressed

No Comments

No Known Activations