INDEX

Explanations

code-related syntax and formatting specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 محفوظة

-0.51

 interessiert

-0.49

#+#

-0.43

 seguida

-0.43

->_

-0.42

SL

-0.41

'],'

-0.40

azt

-0.40

 rubrique

-0.40

RuleContext

-0.40

POSITIVE LOGITS

 فريبيس

0.84

 متعلقه

0.80

 للاسماء

0.76

 שוליים

0.63

 unknownFields

0.62

↵

0.61

ContentAsync

0.59

الحياه

0.59

 >=",

0.58

 initComponents

0.57

Activations Density 0.047%

code-related syntax and formatting specifications

No Comments

No Known Activations