INDEX

Explanations

assertions and conclusions based on research findings

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

Follows a verb of perception or cognition

np_acts-logits-general · gemini-2.0-flash

perceiving information and forming beliefs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.94

 resourceCulture

-0.92

TestingModule

-0.89

сылкі

-0.84

ReusableCell

-0.79

الإنجليزية

-0.79

WindowConstants

-0.78

Personendaten

-0.78

ItemBackground

-0.77

mergeFrom

-0.74

POSITIVE LOGITS

 wonder

0.59

 hypothe

0.57

 observe

0.47

wonder

0.46

 Liszt

0.46

 Perc

0.46

 believe

0.46

 wondering

0.45

say

0.45

 imagine

0.44

Activations Density 1.088%

assertions and conclusions based on research findings

Follows a verb of perception or cognition

perceiving information and forming beliefs

No Comments

No Known Activations