INDEX

Explanations

terms related to well-being and efficacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ьаж

-0.89

Демографія

-0.86

 Signalez

-0.80

 surla

-0.79

 Paglinawan

-0.76

 pinulongan

-0.74

 IndexPath

-0.74

참고

-0.74

 BoxDecoration

-0.73

IntoConstraints

-0.72

POSITIVE LOGITS

 पी

0.43

 ujarnya

0.42

ít

0.42

us

0.42

데

0.41

’

0.41

Sie

0.41

 kamu

0.41

him

0.41

dem

0.41

Activations Density 0.185%

terms related to well-being and efficacy

No Comments

No Known Activations