INDEX

Explanations

references to specific assertions or claims within the text

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

 colorless

-0.58

 pleaſure

-0.58

 colourless

-0.58

 jati

-0.57

Palmarès

-0.57

tanooga

-0.56

skj

-0.55

psz

-0.55

BeNil

-0.54

 pleaf

-0.54

POSITIVE LOGITS

QMetaType

0.74

WithIOException

0.68

HasForeignKey

0.66

WebMethod

0.61

#+#

0.59

 وأن

0.59

Hozzáférés

0.58

HasIndex

0.57

windowFixed

0.56

 mergeFrom

0.55

Activations Density 0.137%

references to specific assertions or claims within the text

No Comments

No Known Activations