INDEX

Explanations

instances of the word "go" and its variations

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

before "to" or a place

np_acts-logits-general · gemini-2.0-flash

go and movement

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

 nakalista

-0.61

 Jurist

-0.50

ptest

-0.49

Ữ

-0.48

>{"

-0.48

ğlu

-0.46

icles

-0.45

儡

-0.45

輯

-0.45

 Cockpit

-0.44

POSITIVE LOGITS

StoryboardSegue

0.88

 GenerationType

0.83

 shopping

0.76

 تضيفلها

0.70

lapsingToolbar

0.69

 Signalez

0.69

 Мексичка

0.67

 ahead

0.66

 forth

0.66

 ashore

0.65

Activations Density 0.105%

instances of the word "go" and its variations

before "to" or a place

go and movement

No Comments

No Known Activations