INDEX

Explanations

specific terms related to scientific reports or research findings

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

Code, symbols, and punctuation

np_acts-logits-general · gemini-2.0-flash

roots, α, sign, work, samples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ricle

-0.58

\\[

-0.51

 components

-0.51

 perbedaan

-0.51

{\

-0.50

principalColumn

-0.49

льки

-0.48

Portail

-0.48

 errori

-0.48

unsqueeze

-0.48

POSITIVE LOGITS

SBATCH

0.88

coaster

0.82

 juſt

0.81

Efq

0.79

NameInMap

0.78

 doubtnut

0.78

 Socorro

0.77

 ſeveral

0.77

 raiſ

0.75

 themſelves

0.74

Activations Density 0.550%

specific terms related to scientific reports or research findings

Code, symbols, and punctuation

roots, α, sign, work, samples

No Comments

No Known Activations