INDEX

Explanations

programming-related snippets, particularly focusing on code structure and syntax elements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kep

-0.58

esp

-0.52

oprot

-0.51

his

-0.51

//*[@

-0.50

 previs

-0.48

 Nach

-0.47

 impe

-0.46

ddr

-0.45

POSITIVE LOGITS

 Majefty

0.97

ſelves

0.97

 AssemblyTitle

0.93

BeginInit

0.90

 itſelf

0.90

 myſelf

0.89

 becauſe

0.87

 themſelves

0.85

 leaſt

0.85

ſelf

0.85

Activations Density 0.034%

programming-related snippets, particularly focusing on code structure and syntax elements

No Comments

No Known Activations