INDEX

Explanations

instances of the word "Essar" followed by varying degrees of relevance-related words, or the word "Essentials"

oai_token-act-pair · gpt-3.5-turbo

the brand "Ess" and its associations 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

 sight

-0.70

è¦ļéĨĴ

-0.68

ategory

-0.65

btn

-0.61

²¾

-0.61

faced

-0.61

=-=-=-=-=-=-=-=-

-0.61

ãĥ£

-0.60

Interested

-0.59

outine

-0.59

POSITIVE LOGITS

entials

1.58

endon

1.25

ences

1.24

ential

1.03

ensible

0.99

entially

0.97

inite

0.95

aults

0.91

linger

0.90

gard

0.90

Activations Density 0.010%

instances of the word "Essar" followed by varying degrees of relevance-related words, or the word "Essentials"

the brand "Ess" and its associations in various contexts

No Comments

No Known Activations