INDEX

Explanations

words and phrases indicating correct or incorrect answers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rungsseite

-0.92

TemporalType

-0.85

CopyWith

-0.85

 GenerationType

-0.73

GEBURTSDATUM

-0.70

 تضيفلها

-0.68

jsonwebtoken

-0.68

AxisAlignment

-0.66

dafx

-0.65

schung

-0.61

POSITIVE LOGITS

PerformLayout

0.64

enough

0.60

 enough

0.56

semibold

0.56

 Burning

0.56

PositiveButton

0.55

AddHtmlAttribute

0.55

ๆ

0.55

est

0.54

SECURE

0.54

Activations Density 0.567%

words and phrases indicating correct or incorrect answers

No Comments

No Known Activations