INDEX

Explanations

references to reading or browsing activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 écou

-0.62

 suffit

-0.61

 policiales

-0.61

 whereof

-0.60

berdayakan

-0.58

tritte

-0.58

 rispet

-0.58

fraid

-0.58

 relatifs

-0.57

 CascadeType

-0.57

POSITIVE LOGITS

 Reading

2.43

Reading

2.30

 reading

2.25

 READING

2.05

reading

1.98

READING

1.84

 readings

1.61

 Readings

1.42

Readings

1.30

 lectura

1.12

Activations Density 0.088%

references to reading or browsing activities

No Comments

No Known Activations