INDEX

Explanations

patterns and comparisons in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 gawas

-0.53

setVerticalGroup

-0.52

 surla

-0.52

 ISNI

-0.51

aarrggbb

-0.47

 لعب

-0.47

CodedInputStream

-0.46

|}\

-0.46

ndice

-0.46

eces

-0.45

POSITIVE LOGITS

 isEqualToString

0.81

 AssemblyTitle

0.71

startswith

0.66

']=='

0.65

 great

0.62

=='

0.61

hasClass

0.60

గ్

0.59

=="

0.59

readystatechange

0.57

Activations Density 0.119%

patterns and comparisons in code snippets

No Comments

No Known Activations