INDEX

Explanations

occurrences of the word "input."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Theſe

-0.70

 itſelf

-0.66

Efq

-0.64

 myſelf

-0.63

 Majefty

-0.62

 himſelf

-0.61

 pleaſure

-0.60

 Houſe

-0.58

 leaſt

-0.58

 Demos

-0.58

POSITIVE LOGITS

input

2.70

 input

1.75

Input

1.59

 Input

1.55

INPUT

1.49

 INPUT

1.32

输入

1.03

 inputs

1.02

InputElement

0.91

inputs

0.90

Activations Density 0.098%

occurrences of the word "input."

No Comments

No Known Activations