INDEX

Explanations

instances of the word "Word" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to the word processing software "Word" and related terminology

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

asio

-0.76

rero

-0.73

 unnecess

-0.73

alus

-0.73

OHN

-0.70

 Pradesh

-0.70

ocal

-0.69

Interstitial

-0.68

\/\/

-0.67

 unaff

-0.67

POSITIVE LOGITS

sworth

1.28

press

1.13

 Word

0.98

 Trafford

0.84

ifier

0.84

Perfect

0.83

ptr

0.80

Word

0.79

matical

0.76

speak

0.75

Activations Density 0.016%

instances of the word "Word" in various contexts

references to the word processing software "Word" and related terminology

No Comments

No Known Activations