INDEX

Explanations

terms related to segments and their classifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

</table>

-0.77

ed

-0.76

eyes

-0.75

endphp

-0.74

Transcripción

-0.74

 Czer

-0.74

ا

-0.74

 airflow

-0.72

xase

-0.71

POSITIVE LOGITS

 sement

1.08

uent

1.00

ant

0.92

ulant

0.87

ANT

0.86

lent

0.86

nent

0.86

tant

0.86

EMENT

0.84

ent

0.83

Activations Density 0.413%

terms related to segments and their classifications in various contexts

No Comments

No Known Activations