INDEX

Explanations

phrases or terms indicating comparisons or relationships in a relative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 asiatique

-0.85

 épis

-0.83

 bancaire

-0.82

 régle

-0.80

MemoryWarning

-0.78

InstanceState

-0.76

 panoramique

-0.75

 métallique

-0.74

 polaire

-0.74

 quelquefois

-0.74

POSITIVE LOGITS

Gri

0.91

 apply

0.69

 Apply

0.69

 APPLY

0.68

gri

0.66

Apply

0.66

Gri

0.65

Applying

0.64

 applying

0.62

APPLY

0.62

Activations Density 0.093%

phrases or terms indicating comparisons or relationships in a relative context

No Comments

No Known Activations