INDEX

Explanations

code-related structures and elements, likely related to programming or markup languages

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

InputTagHelper

-0.71

OGND

-0.67

printLine

-0.64

writeFieldEnd

-0.60

LabelTagHelper

-0.58

 tartalomajánló

-0.54

 '\\;'

-0.53

NoSuchAlgorithm

-0.52

 composés

-0.51

 lehetős

-0.51

POSITIVE LOGITS

="../

0.82

 обращения

0.72

cpp

0.69

ClientSize

0.68

loadModel

0.65

 filename

0.63

AccessorTable

0.58

toggler

0.58

 مشين

0.58

 ویکی‌پدیای

0.58

Activations Density 0.053%

code-related structures and elements, likely related to programming or markup languages

No Comments

No Known Activations