INDEX

Explanations

features related to personal abilities and achievements

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

Auxiliary verbs followed by main verbs

np_acts-logits-general · gemini-2.0-flash

positive outcomes from actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 démoc

-0.51

 popolari

-0.49

formKey

-0.48

CodedInputStream

-0.48

Revenir

-0.47

 olun

-0.47

dataclass

-0.46

AdapterView

-0.46

ragment

-0.45

anyahu

-0.45

POSITIVE LOGITS

 earn

0.81

 landed

0.79

 earned

0.78

 earns

0.76

 earning

0.75

 entitle

0.74

 catapult

0.74

CloseOperation

0.71

 propel

0.70

 catap

0.70

Activations Density 0.355%

features related to personal abilities and achievements

Auxiliary verbs followed by main verbs

positive outcomes from actions

No Comments

No Known Activations