INDEX

Explanations

programming class names and related terms

oai_token-act-pair · gpt-3.5-turbo

programming language class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

OPLE

-0.71

cean

-0.68

STON

-0.68

yssey

-0.67

Ö

-0.67

hiba

-0.66

vous

-0.64

ternity

-0.63

 wrought

-0.63

 mammoth

-0.63

POSITIVE LOGITS

ifier

1.18

ifications

1.16

ifies

1.13

ifiers

1.12

ifying

1.02

ification

0.97

path

0.94

ifiable

0.93

classes

0.91

ified

0.90

Activations Density 0.018%

programming class names and related terms

programming language class definitions

No Comments

No Known Activations