INDEX

Explanations

instances of the letter 'e' in various contexts

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

Followed by parentheses, brackets, or slashes

np_acts-logits-general · gemini-2.0-flash

exception handling or 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

mergeFrom

-0.52

 AssemblyCompany

-0.52

DebuggerStep

-0.49

GOTREF

-0.49

Lo

-0.46

nimmt

-0.46

ERIES

-0.44

stall

-0.43

JoinTable

-0.42

loped

-0.42

POSITIVE LOGITS

TypedDataSet

0.71

ContentAsync

0.69

tagHelperRunner

0.65

rungsseite

0.61

OGND

0.61

Rüyada

0.61

 незавершена

0.59

 occafion

0.59

 onCancelled

0.58

AccessorTable

0.57

Activations Density 0.094%

instances of the letter 'e' in various contexts

Followed by parentheses, brackets, or slashes

exception handling or code syntax

No Comments

No Known Activations