INDEX

Explanations

terms related to molecular electronics and materials science

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

versus and against

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 ujednoznacz

-0.75

原始内容存档于

-0.62

NUMX

-0.60

annique

-0.60

])):

-0.60

AutoScaleMode

-0.59

Архівовано

-0.58

 }}$}

-0.56

 상세

-0.55

Билгалдахарш

-0.54

POSITIVE LOGITS

vs

0.90

 versus

0.78

Vs

0.68

 Versus

0.66

 against

0.59

vs

0.58

VS

0.57

与

0.56

與

0.54

Against

0.51

Activations Density 0.267%

terms related to molecular electronics and materials science

versus and against

No Comments

No Known Activations