INDEX

Explanations

terms related to compensation and financial remuneration

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-1.36

 HasFactory

-1.21

oredCriteria

-1.18

 MainAxisSize

-1.17

abestanden

-1.12

ftagPool

-1.11

 propOrder

-1.10

 itſelf

-1.09

AndEndTag

-1.08

PreferredItem

-1.08

POSITIVE LOGITS

0.84

0.74

↵↵

0.70

0.69

↵

0.69

0.68

0.66

<eos>

0.64

 primary

0.63

Activations Density 0.144%

terms related to compensation and financial remuneration

No Comments

No Known Activations