INDEX

Explanations

phrases and words indicating potential outcomes and consequences related to decisions or events

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

 AssemblyCulture

-0.74

Jîn

-0.57

 uſe

-0.57

 chofe

-0.57

Personensuche

-0.53

 wako

-0.53

MockMvc

-0.52

脚注の使い方

-0.51

 pierde

-0.51

 forgetting

-0.51

POSITIVE LOGITS

 impact

0.85

 significantly

0.82

 result

0.79

impact

0.74

 impacts

0.74

 profoundly

0.72

 dramatically

0.72

Impact

0.70

IMPACT

0.70

 Impact

0.70

Activations Density 0.393%

phrases and words indicating potential outcomes and consequences related to decisions or events

No Comments

No Known Activations