INDEX

Explanations

phrases describing individuals' personal backgrounds, achievements, and professional roles

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

preceding descriptions of people

np_acts-logits-general · gemini-2.0-flash

a member role

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

StoryboardSegue

-0.64

ьаж

-0.63

NewUrlParser

-0.57

itoriale

-0.55

LookAnd

-0.55

 fewest

-0.55

 Anthropological

-0.53

 alfab

-0.53

writeFieldEnd

-0.52

 Shakspeare

-0.52

POSITIVE LOGITS

 member

1.22

 participant

1.00

 frequent

0.93

 avid

0.91

member

0.87

participant

0.85

frequent

0.85

 ardent

0.83

 graduate

0.82

 founding

0.82

Activations Density 0.241%

phrases describing individuals' personal backgrounds, achievements, and professional roles

preceding descriptions of people

a member role

No Comments

No Known Activations