INDEX

Explanations

phrases indicating additional information or elaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 firebaseConfig

-0.64

complexType

-0.63

JspWriter

-0.58

rófono

-0.58

 kokona

-0.56

 väli

-0.54

IsContent

-0.54

 Hopf

-0.54

 ilman

-0.54

vertx

-0.53

POSITIVE LOGITS

Autoritní

0.73

let

0.61

__':

0.60

rungsseite

0.59

MessageTagHelper

0.54

 also

0.53

ografija

0.53

 كورة

0.50

 للاسماء

0.50

 resourceCulture

0.50

Activations Density 0.170%

phrases indicating additional information or elaboration

No Comments

No Known Activations