INDEX

Explanations

phrases discussing the relationship between actions and their irrelevance or independence from certain subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 volgt

-0.55

Ethical

-0.52

Dougall

-0.50

tiefel

-0.50

ActivityCompat

-0.50

 Ethical

-0.49

FormBorderStyle

-0.49

fractive

-0.48

 suivre

-0.47

 adicionales

-0.46

POSITIVE LOGITS

protoimpl

0.72

($__

0.70

بوابة

0.69

principalTable

0.69

 unrelated

0.68

]")]

0.68

related

0.67

 GenerationType

0.67

+#+#

0.66

SerializedName

0.66

Activations Density 0.156%

phrases discussing the relationship between actions and their irrelevance or independence from certain subjects

No Comments

No Known Activations