INDEX

Explanations

symbols and references to various typing formats or annotations

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

-0.53

ysław

-0.50

ainya

-0.48

 recu

-0.46

من

-0.45

 useNavigate

-0.44

 Trä

-0.43

ArgsConstructor

-0.43

POSITIVE LOGITS

 beginnetje

0.95

OGND

0.93

LookAnd

0.87

그리고

0.79

addCriterion

0.76

Và

0.75

snd

0.75

 κι

0.73

spesies

0.73

DockStyle

0.71

Activations Density 0.223%

symbols and references to various typing formats or annotations

No Comments

No Known Activations