INDEX

Explanations

phrases related to promotional offers and trials for services or products

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

tests or trying

np_acts-logits-general · gemini-2.0-flash

trial or testing words

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.69

Obrázky

-0.61

 ArrayAdapter

-0.60

 purpoſe

-0.58

SBATCH

-0.56

ResumeLayout

-0.54

PerformLayout

-0.54

OCCURRED

-0.54

 onPage

-0.54

 pleaſure

-0.54

POSITIVE LOGITS

 test

2.61

 trial

2.55

 testing

2.43

 Test

2.25

 experiment

2.25

 tests

2.22

 tested

2.17

 experimentation

2.14

 Testing

2.12

 experiments

2.11

Activations Density 0.705%

phrases related to promotional offers and trials for services or products

tests or trying

trial or testing words

No Comments

No Known Activations