INDEX

Explanations

phrases and terms related to detailed descriptions and analyses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referenties

-0.62

था

-0.59

 iNdEx

-0.58

initComponents

-0.57

 populi

-0.56

 colch

-0.55

GRAPHY

-0.54

󠁴

-0.54

 légitime

-0.54

 Attitude

-0.53

POSITIVE LOGITS

 detail

1.76

 detailed

1.56

 Detail

1.48

 details

1.47

detailed

1.44

 Detailed

1.43

Detailed

1.43

detail

1.38

 DETAIL

1.30

Detail

1.30

Activations Density 0.319%

phrases and terms related to detailed descriptions and analyses

No Comments

No Known Activations