INDEX

Explanations

references to public statements and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

惫

-0.65

 bezeichneter

-0.62

ωση

-0.61

PointerException

-0.61

innen

-0.60

tigungs

-0.59

 perfección

-0.56

infec

-0.56

skraft

-0.56

 kval

-0.56

POSITIVE LOGITS

 publicly

1.38

 public

1.09

 öffentlich

1.01

 públicas

0.94

 publicized

0.93

 publice

0.90

 publi

0.90

 publico

0.89

 PUBLIC

0.89

 pública

0.88

Activations Density 0.191%

references to public statements and actions

No Comments

No Known Activations