INDEX

Explanations

terms related to transparency and clarity in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Fea

-0.75

mvn

-0.69

rinfo

-0.69

Ell

-0.69

DataMember

-0.68

encodeWith

-0.67

 Stuhl

-0.66

={`/

-0.66

SizeF

-0.64

PMailer

-0.64

POSITIVE LOGITS

 transparency

1.63

 Transparency

1.46

 transparent

1.44

 Transparent

1.43

transparent

1.40

Transparent

1.33

Transparency

1.32

 transpar

1.31

transparency

1.24

 transpa

1.14

Activations Density 0.071%

terms related to transparency and clarity in communication

No Comments

No Known Activations