INDEX

Explanations

references to promises and commitments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Italijanski

-0.59

RenderAtEndOf

-0.59

مراجع

-0.49

 indisponible

-0.47

rawDesc

-0.45

 rette

-0.43

ilación

-0.43

 Cách

-0.43

 Auff

-0.42

 disliked

-0.42

POSITIVE LOGITS

 promise

3.32

 promises

2.99

promise

2.73

 promised

2.72

 Promise

2.69

Promise

2.54

 Promises

2.51

 pledge

2.51

promises

2.43

 pledges

2.39

Activations Density 0.480%

references to promises and commitments

No Comments

No Known Activations

references to promises and commitments

No Comments

No Known Activations