INDEX

Explanations

terms related to programming or computational structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.71

Efq

-0.58

jsdelivr

-0.58

dafx

-0.58

]<=

-0.57

\}^{

-0.56

 Guil

-0.54

 remplacement

-0.54

]=="

-0.53

haviors

-0.52

POSITIVE LOGITS

 ModelExpression

0.66

 added

0.59

طوب

0.58

sizeCache

0.56

TextHelper

0.52

corporated

0.48

 actionTypes

0.48

 Added

0.47

ymce

0.47

moveToFirst

0.46

Activations Density 1.375%

terms related to programming or computational structures

No Comments

No Known Activations