INDEX

Explanations

instructions related to adding configurations and parameters in testing software

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

Punctuation followed by capitalization

np_acts-logits-general · gemini-2.0-flash

marks sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

{'

-0.54

 shameful

-0.53

[++

-0.52

 shaming

-0.50

shame

-0.50

بدو

-0.49

‘

-0.48

gridx

-0.48

 AttributeSet

-0.48

StoreMessageInfo

-0.47

POSITIVE LOGITS

 houſe

0.94

 pleaſure

0.85

 ſtand

0.82

 whoſe

0.81

 raiſ

0.80

 ſtate

0.80

 becauſe

0.79

 deſt

0.77

ſelf

0.77

Efq

0.76

Activations Density 0.603%

instructions related to adding configurations and parameters in testing software

Punctuation followed by capitalization

marks sentence endings

No Comments

No Known Activations