INDEX

Explanations

the presence of specific formatting or document structure indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ftagPool

-0.60

PullParser

-0.57

 ivelany

-0.53

domada

-0.53

Amicalement

-0.50

msgSender

-0.47

Viitteet

-0.47

VolleyError

-0.47

galus

-0.46

PhysRevLett

-0.45

POSITIVE LOGITS

Tikang

1.05

AnchorStyles

0.80

memoized

0.68

Enllaces

0.67

حياته

0.63

❋

0.63

 Reverso

0.61

ResumeLayout

0.60

rungsseite

0.59

 kasarigan

0.59

Activations Density 0.321%

the presence of specific formatting or document structure indicators

No Comments

No Known Activations