INDEX

Explanations

words related to the prefix "der" and its variations, indicating a focus on words derived from that prefix

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nakalista

-0.66

findpost

-0.64

 Autorisations

-0.61

ViewFeatures

-0.60

 Neel

-0.58

tvguidetime

-0.55

 transférez

-0.55

ABUL

-0.55

Dữ

-0.55

úrese

-0.55

POSITIVE LOGITS

DER

0.65

 CURLOPT

0.59

GetMapping

0.59

AddTagHelper

0.59

LookAnd

0.57

LabelTagHelper

0.56

went

0.55

ollectionView

0.55

曖昧さ回避

0.54

 Мексичка

0.54

Activations Density 0.102%

words related to the prefix "der" and its variations, indicating a focus on words derived from that prefix

No Comments

No Known Activations