INDEX

Explanations

statements or declarations that convey an important conclusion or sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

期刊论文

-0.62

astéro

-0.62

Again

-0.60

 Again

-0.58

 estimés

-0.53

"]();

-0.53

AGAIN

-0.50

()]);

-0.49

 ampla

-0.49

again

-0.48

POSITIVE LOGITS

 even

0.74

 judging

0.72

 apart

0.71

 maybe

0.70

 there

0.68

 perhaps

0.67

 facing

0.65

 ordinary

0.63

 seeing

0.61

 under

0.60

Activations Density 0.020%

statements or declarations that convey an important conclusion or sentiment

No Comments

No Known Activations

statements or declarations that convey an important conclusion or sentiment

No Comments

No Known Activations