INDEX

Explanations

references to specific organizations and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ngdoc

-0.60

OpenHelper

-0.54

 BoxFit

-0.53

 OnInit

-0.52

jfree

-0.50

auff

-0.49

IV

-0.48

AddTagHelper

-0.48

 Zool

-0.47

hdysval

-0.47

POSITIVE LOGITS

 poffe

0.62

Affirmed

0.61

 pleaſure

0.60

 federation

0.59

 neceff

0.59

 fotografico

0.58

CopyWith

0.58

 ftate

0.56

 ſhe

0.56

 lyre

0.56

Activations Density 0.369%

references to specific organizations and their activities

No Comments

No Known Activations