INDEX

Explanations

references to numerical values and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-1.14

 myſelf

-1.13

 themſelves

-1.05

 pleaſure

-1.00

 reaſon

-0.98

ſelf

-0.97

 purpoſe

-0.97

^(@)

-0.96

ſelves

-0.95

 Jefus

-0.95

POSITIVE LOGITS

the

1.16

<eos>

0.93

the

0.82

0.74

The

0.68

↵↵↵

0.64

THE

0.61

his

0.60

0.57

Activations Density 0.458%

references to numerical values and statistics

No Comments

No Known Activations