INDEX

Explanations

programming-related syntax and identifiers

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

Variables or code snippets

np_acts-logits-general · gemini-2.0-flash

programming code syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Ko

-0.55

pecially

-0.54

-0.49

aturday

-0.47

AMAHA

-0.47

signol

-0.46

ruary

-0.46

ecznie

-0.46

UAGE

-0.46

inière

-0.45

POSITIVE LOGITS

 pleaſure

1.09

 Theſe

0.98

 raiſ

0.92

 myſelf

0.92

 fubject

0.91

 ſeveral

0.91

 purpoſe

0.88

 greateſt

0.88

 ſtate

0.87

 cauſe

0.86

Activations Density 0.838%

programming-related syntax and identifiers

Variables or code snippets

programming code syntax

No Comments

No Known Activations