INDEX

Explanations

repeated numerical values or sequences in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.07

ſelf

-1.07

Efq

-1.04

 ་་

-1.04

 Jefus

-1.01

 ―――――

-1.00

 raiſ

-0.94

ſelves

-0.93

 Majefty

-0.92

DockStyle

-0.92

POSITIVE LOGITS

two

1.03

 three

0.99

 four

0.94

two

0.91

 deux

0.86

 trois

0.84

 five

0.84

big

0.82

 zwei

0.81

Two

0.81

Activations Density 0.584%

repeated numerical values or sequences in the text

No Comments

No Known Activations