INDEX

Explanations

terms related to data handling, specifically in the context of database sessions and file operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

=>"

-0.73

 ostavi

-0.68

[];

-0.67

 ...]

-0.62

styleable

-0.59

[],

-0.59

]='\

-0.58

->___

-0.58

 "..\..\..\

-0.58

baugh

-0.57

POSITIVE LOGITS

 fusca

0.67

Slf

0.62

 createState

0.60

0.57

consulté

0.55

 noDo

0.54

 MonoBehaviour

0.54

Przypisy

0.51

 Sopho

0.51

 tanong

0.51

Activations Density 0.266%

terms related to data handling, specifically in the context of database sessions and file operations

No Comments

No Known Activations