INDEX

Explanations

references to legal cases and judicial decisions

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

Follows a dot

np_acts-logits-general · gemini-2.0-flash

de followed by names

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 purpoſe

-0.58

chymal

-0.54

 '\\;'

-0.53

WriteTagHelper

-0.53

DMX

-0.53

CloseOperation

-0.53

TagMode

-0.52

 tfsi

-0.52

raborty

-0.51

parsedMessage

-0.51

POSITIVE LOGITS

PPS

0.68

PP

0.61

PW

0.59

PPS

0.59

ValueStyle

0.56

PP

0.56

Попис

0.55

 NSCoder

0.54

PPD

0.54

Activations Density 0.742%

references to legal cases and judicial decisions

Follows a dot

de followed by names

No Comments

No Known Activations