INDEX

Explanations

terms related to food and dining

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Roskov

-1.11

 itſelf

-1.05

 myſelf

-0.97

RenderAtEndOf

-0.97

tagHelperRunner

-0.95

$_"

-0.95

neſs

-0.94

 Anſ

-0.93

Efq

-0.92

 Houſe

-0.91

POSITIVE LOGITS

 fare

0.77

cls

0.69

</i>

0.62

 playlist

0.57

0.56

</b>

0.54

fare

0.53

</sup>

0.52

 signatures

0.52

 play

0.51

Activations Density 0.161%

terms related to food and dining

No Comments

No Known Activations