INDEX

Explanations

negative qualifiers or expressions that convey negation

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

 TableColumn

-0.71

 esmeralda

-0.69

httphttps

-0.67

 Kuba

-0.65

 parcourir

-0.65

TypeEnum

-0.65

ogeneous

-0.65

 Belk

-0.64

 dorada

-0.64

struck

-0.62

POSITIVE LOGITS

Not

1.01

Not

0.99

Quite

0.90

 Quite

0.90

 quite

0.89

CloseOperation

0.88

 Trent

0.86

 estimés

0.84

not

0.81

NOT

0.81

Activations Density 0.116%

negative qualifiers or expressions that convey negation

No Comments

No Known Activations