INDEX

Explanations

references to political processes and their implications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.81

and

-0.64

EndProject

-0.64

as

-0.61

but

-0.60

 והוא

-0.52

Референце

-0.52

があり

-0.52

ніципа

-0.50

 because

-0.50

POSITIVE LOGITS

 purpoſe

0.95

 ſever

0.95

 themſelves

0.94

 ſche

0.94

 Conſ

0.93

 pleaſure

0.90

 itſelf

0.89

 ſmall

0.87

 unſ

0.86

 Reſ

0.86

Activations Density 1.704%

references to political processes and their implications

No Comments

No Known Activations