INDEX

Explanations

references to food-related concepts, specifically cooking and preparation

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

 CreateTagHelper

-1.11

uxxxx

-0.91

Efq

-0.90

AddTagHelper

-0.89

 Paglinawan

-0.87

AnchorStyles

-0.82

DockStyle

-0.80

 Signalez

-0.80

 utafitiHapana

-0.79

 myſelf

-0.78

POSITIVE LOGITS

0.51

0.48

0.45

0.43

is

0.43

0.42

Activations Density 0.203%

references to food-related concepts, specifically cooking and preparation

No Comments

No Known Activations