INDEX

Explanations

technical terminology and concepts related to proofs and methodologies in scientific literature

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

Applicability, application, and extensions of results or methods

np_acts-logits-general · gemini-2.0-flash

applicable generalizes

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

COUVER

-0.64

 yerine

-0.57

enderror

-0.55

WriteBarrier

-0.55

 tué

-0.52

LabelTagHelper

-0.51

quartile

-0.49

ScopeManager

-0.48

lidays

-0.48

 Marav

-0.47

POSITIVE LOGITS

 applicable

0.98

applicable

0.91

 applicability

0.90

 Applicable

0.86

 applies

0.81

 APPLICABLE

0.81

Applicable

0.80

 apply

0.79

 aplicable

0.75

 generalize

0.71

Activations Density 0.625%

technical terminology and concepts related to proofs and methodologies in scientific literature

Applicability, application, and extensions of results or methods

applicable generalizes

No Comments

No Known Activations