INDEX

Explanations

references to specific entities or elements across 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

 großes

-0.52

лих

-0.47

ográficas

-0.46

خرى

-0.45

TextAppearance

-0.45

Unnamed

-0.45

 Table

-0.45

gnant

-0.44

 нет

-0.44

чів

-0.44

POSITIVE LOGITS

 nakalista

0.92

 ExecuteAsync

0.70

 présidenti

0.70

__(/*!

0.68

 healthiest

0.65

+#+#

0.65

 widest

0.64

 tallest

0.63

 pageContext

0.63

"]));

0.63

Activations Density 0.618%

references to specific entities or elements across various contexts

No Comments

No Known Activations