INDEX

Explanations

patterns involving the phrase "to be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SequentialGroup

-0.69

ież

-0.59

didSet

-0.55

 adiabatic

-0.55

 Picchu

-0.53

worfen

-0.52

IntoConstraints

-0.52

AndEndTag

-0.52

etine

-0.51

 REMEMBER

-0.48

POSITIVE LOGITS

ſelf

0.85

 itſelf

0.85

ſelves

0.79

Efq

0.77

=""></

0.76

 Monfieur

0.74

 purpoſe

0.72

 myſelf

0.72

Бахар

0.68

 Theſe

0.66

Activations Density 0.268%

patterns involving the phrase "to be" in various contexts

No Comments

No Known Activations