INDEX

Explanations

mentions of "input" and related terminology in the context of programming or data handling

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

SharedCtor

-0.88

 HasFactory

-0.64

Parcelize

-0.64

enumi

-0.61

 initComponents

-0.60

WebServlet

-0.59

saraba

-0.59

QtWidgets

-0.58

RTLD

-0.58

ⓘ

-0.57

POSITIVE LOGITS

ting

0.73

ted

0.64

pement

0.60

Output

0.58

output

0.57

 Output

0.57

гән

0.56

orescence

0.55

OUTPUT

0.55

 متعلقه

0.54

Activations Density 0.118%

mentions of "input" and related terminology in the context of programming or data handling

No Comments

No Known Activations