INDEX

Explanations

computer programming terms related to defining constants and fields

oai_token-act-pair · gpt-3.5-turbo

specific entities or terms related to scientific and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dire

-0.64

 Adin

-0.61

 downstream

-0.59

ument

-0.58

 Thornton

-0.58

 Compass

-0.57

POS

-0.57

 Palest

-0.57

 Crus

-0.56

UD

-0.56

POSITIVE LOGITS

ogether

0.72

ONSORED

0.67

vernight

0.66

<-

0.66

ifully

0.65

--------------------------------------------------------

0.65

APTER

0.63

isine

0.63

EVA

0.61

urally

0.61

Activations Density 0.379%

computer programming terms related to defining constants and fields

specific entities or terms related to scientific and technical contexts

No Comments

No Known Activations