INDEX

Explanations

structural markers indicating the beginning of text segments or sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

י

-0.59

ho

-0.58

-0.56

 quartiers

-0.56

ark

-0.56

 Aoki

-0.55

 marks

-0.55

 Duff

-0.54

pen

-0.54

 Ruin

-0.54

POSITIVE LOGITS

msub

2.83

msup

2.10

msubsup

1.70

mfrac

1.22

AddTagHelper

1.19

 FetchType

1.13

erover

1.12

)";

1.08

 فريبيس

1.06

HasForeignKey

1.03

Activations Density 0.066%

structural markers indicating the beginning of text segments or sections

No Comments

No Known Activations