INDEX

Explanations

phrases and terms related to reputation and recognition in 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 @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 ModelExpression

-0.65

typeorm

-0.65

awaiter

-0.64

◀

-0.64

AnchorStyles

-0.62

Wpf

-0.61

npos

-0.59

parsedMessage

-0.59

 SPOILERS

-0.59

ichtete

-0.58

POSITIVE LOGITS

 reputation

1.30

 réputation

1.08

 reputations

1.08

 Reputation

1.00

 reputación

0.98

 reputa

0.97

 notoriety

0.92

 renown

0.90

Reputation

0.89

 repute

0.84

Activations Density 0.224%

phrases and terms related to reputation and recognition in various contexts

No Comments

No Known Activations