INDEX

Explanations

articles and determiners in text

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

Followed by different words

np_acts-logits-general · gemini-2.0-flash

la bande, la version, la solution, la radio

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

 Shakspeare

-0.94

 houſe

-0.93

 Chriftian

-0.89

 Monfieur

-0.89

 Houſe

-0.87

 Cæsar

-0.87

 ſche

-0.84

 purpoſe

-0.84

 pleaſure

-0.83

Efq

-0.82

POSITIVE LOGITS

 same

1.23

 most

1.08

 latter

1.03

 last

0.93

 final

0.91

 entire

0.89

 main

0.83

 whole

0.83

 rest

0.83

 fact

0.82

Activations Density 0.018%

articles and determiners in text

Followed by different words

la bande, la version, la solution, la radio

No Comments

No Known Activations