INDEX

Explanations

technical terms or actions related to computer programming or data processing

oai_token-act-pair · gpt-3.5-turbo

terms related to instructions, measurements, and connections in various contexts

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

 Vest

-0.57

CHAT

-0.55

 Originally

-0.52

oln

-0.52

algia

-0.51

 Utility

-0.50

 Veteran

-0.49

 FANTASY

-0.49

 Supplemental

-0.48

 Apart

-0.48

POSITIVE LOGITS

 imaginable

0.76

çķ

0.64

_.

0.63

 mosqu

0.63

ãĤ´ãĥ³

0.59

arsity

0.59

 mates

0.58

ãĤ·

0.57

otype

0.57

.</

0.57

Activations Density 0.838%

technical terms or actions related to computer programming or data processing

terms related to instructions, measurements, and connections in various contexts

No Comments

No Known Activations