INDEX

Explanations

colons and formatting indicators

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

 myſelf

-4.29

Efq

-4.11

 itſelf

-3.94

 Monfieur

-3.90

 Theſe

-3.85

 Jefus

-3.74

 Majefty

-3.62

 pleaſure

-3.60

 ―――――

-3.58

 ſeveral

-3.53

POSITIVE LOGITS

2.23

2.11

2.10

2.09

2.07

2.03

1.87

<eos>

1.79

↵↵

1.76

in

1.74

Activations Density 0.536%

colons and formatting indicators

No Comments

No Known Activations