INDEX

Explanations

proper nouns or names, particularly of individuals or entities

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.91

 liegenden

-0.75

 начинают

-0.65

Sasuke

-0.65

 south

-0.64

 سعيد

-0.61

 становятся

-0.60

 southwest

-0.60

 east

-0.60

POSITIVE LOGITS

 stockholm

1.47

 inder

1.44

 overla

1.41

 accla

1.40

 peppa

1.38

 zimmer

1.37

 bett

1.35

 abbra

1.35

 milf

1.34

 blin

1.33

Activations Density 0.327%

proper nouns or names, particularly of individuals or entities

No Comments

No Known Activations