INDEX

Explanations

the word "than" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

comparative phrases indicating alternatives or exceptions

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

Accessory

-0.70

 veter

-0.70

overed

-0.68

 Takeru

-0.67

aced

-0.67

acia

-0.67

lied

-0.66

 Azerb

-0.64

iona

-0.63

uese

-0.62

POSITIVE LOGITS

 ours

0.70

 hers

0.69

 namely

0.67

 outright

0.62

ascript

0.61

 those

0.58

awks

0.56

 wish

0.56

ensical

0.56

 theirs

0.56

Activations Density 0.029%

the word "than" followed by a numerical value

comparative phrases indicating alternatives or exceptions

No Comments

No Known Activations