INDEX

Explanations

technical terms and programming instructions

oai_token-act-pair · gpt-3.5-turbo

technical identifiers or metadata related to documents or content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

etheless

-0.62

©¶æ

-0.57

 Gors

-0.49

DragonMagazine

-0.46

Ĥİ

-0.46

NCT

-0.43

inventoryQuantity

-0.42

 enthusi

-0.41

asking

-0.41

govtrack

-0.40

POSITIVE LOGITS

 [âĢ¦]

0.43

 glor

0.40

ent

0.39

 (Â£

0.38

 delic

0.38

imb

0.36

imm

0.35

 imper

0.35

 chip

0.34

 buoy

0.34

Activations Density 3.644%

technical terms and programming instructions

technical identifiers or metadata related to documents or content

No Comments

No Known Activations