INDEX

Explanations

words related to ongoing actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

gdx

-0.93

&__

-0.82

 שוליים

-0.80

 للمعارف

-0.78

 meille

-0.72

 SwiftUI

-0.70

/-/

-0.69

Mes

-0.69

 vertes

-0.69

dersfield

-0.69

POSITIVE LOGITS

 Continue

1.09

 Continues

1.07

 continues

1.02

continuation

1.00

 Continu

1.00

 continued

0.98

 continuing

0.97

 Continuation

0.97

continues

0.96

CONTINUE

0.96

Activations Density 0.059%

words related to ongoing actions or states

No Comments

No Known Activations