INDEX

Explanations

phrases that are interchangeable or closely related to other phrases

oai_token-act-pair · gpt-3.5-turbo

terms associated with being well-known or commonly associated with something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gments

-0.72

abama

-0.68

eneg

-0.68

izons

-0.68

otos

-0.65

phabet

-0.65

ihad

-0.64

 asylum

-0.64

GRE

-0.63

Rae

-0.63

POSITIVE LOGITS

 synonymous

0.78

 ubiqu

0.75

 nowadays

0.74

 Nadu

0.74

 ubiquitous

0.72

 Register

0.70

entimes

0.69

ãĤ¨ãĥ«

0.68

ophobia

0.67

Jet

0.66

Activations Density 0.073%

phrases that are interchangeable or closely related to other phrases

terms associated with being well-known or commonly associated with something

No Comments

No Known Activations