INDEX

Explanations

patterns or structures in code, particularly in relation to internal identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

setVerticalGroup

-0.66

TableHead

-0.64

sidemargin

-0.61

Xna

-0.60

InBackground

-0.58

sschutz

-0.55

DispatchToProps

-0.55

itinéraire

-0.53

 head

-0.53

ObjectMeta

-0.52

POSITIVE LOGITS

 Paglinawan

0.64

 betweenstory

0.53

 AssemblyProduct

0.51

Pyx

0.47

"?>

0.46

sowie

0.45

 Baillargeon

0.45

RenderAtEndOf

0.45

 OTHERWISE

0.44

 Numerade

0.44

Activations Density 0.097%

patterns or structures in code, particularly in relation to internal identifiers

No Comments

No Known Activations