INDEX

Explanations

text that is bolded or emphasized

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

mem

-0.74

}}}}

-0.74

 Zaman

-0.72

midt

-0.71

 אופ

-0.68

 }^{*}

-0.67

orten

-0.67

ACT

-0.66

getLog

-0.65

tat

-0.65

POSITIVE LOGITS

</strong>

1.23

 Phry

0.87

rungsseite

0.86

mmä

0.82

AddTagHelper

0.80

IsMutable

0.77

PerformLayout

0.73

AndEndTag

0.73

!("{

0.71

первых

0.71

Activations Density 0.036%

text that is bolded or emphasized

No Comments

No Known Activations