INDEX

Explanations

phrases related to explanations or causation

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

Follows rationale/explanation words

np_acts-logits-general · gemini-2.0-flash

stating why

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

mybatisplus

-0.66

 vVar

-0.56

}`}

-0.55

PhysRevD

-0.55

}\]

-0.53

mappedBy

-0.52

 виправивши

-0.52

*/].

-0.51

 Administrativna

-0.51

cotch

-0.51

POSITIVE LOGITS

why

1.19

why

0.93

 varför

0.81

 warum

0.80

 mengapa

0.79

Why

0.74

 почему

0.72

 pourquoi

0.70

Why

0.69

为什么

0.69

Activations Density 0.574%

phrases related to explanations or causation

Follows rationale/explanation words

stating why

No Comments

No Known Activations