INDEX

Explanations

phrases expressing preference or desire regarding choices and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

neval

-0.53

клопе

-0.53

ksikon

-0.48

lapsingToolbar

-0.47

Expectations

-0.45

нок

-0.45

|}{}

-0.44

上位

-0.42

γά

-0.42

DBL

-0.42

POSITIVE LOGITS

 prefer

2.56

 preferred

2.38

 prefers

2.37

 Prefer

2.29

prefer

2.25

 preference

2.23

 preferring

2.18

Prefer

2.15

 préfère

2.15

preferred

2.10

Activations Density 0.281%

phrases expressing preference or desire regarding choices and situations

No Comments

No Known Activations