INDEX

Explanations

terms related to the process of extraction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

</b>

-0.84

 Osbourne

-0.71

-0.70

-0.68

-0.67

</i>

-0.66

ಿ

-0.65

気

-0.65

-0.63

POSITIVE LOGITS

 EXTRACT

1.16

 Extract

1.07

 Extracts

1.07

Extract

1.05

 Hunter

1.05

RepeatedField

1.04

 HUNTER

1.04

Geplaatst

1.03

彡

1.00



1.00

Activations Density 0.151%

terms related to the process of extraction

No Comments

No Known Activations