INDEX

Explanations

references to quantities and comparisons in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

makeText

-0.60

 Roskov

-0.56

bergement

-0.52

原始内容存档于

-0.50

protoc

-0.46

 समीक्षाओं

-0.46

 transfieras

-0.45

DebuggerNonUser

-0.44

istoitu

-0.43

 FetchType

-0.43

POSITIVE LOGITS

 single

2.24

single

2.06

ONE

1.99

one

1.93

Single

1.85

 één

1.84

 SINGLE

1.80

 Single

1.72

SINGLE

1.68

 satu

1.59

Activations Density 0.764%

references to quantities and comparisons in data

No Comments

No Known Activations