INDEX

Explanations

words related to the location or entity "Samisa"

oai_token-act-pair · gpt-3.5-turbo

the word "Isa" in various contexts throughout the document

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

tin

-0.75

 subp

-0.73

auld

-0.72

emporary

-0.70

birds

-0.68

roph

-0.68

tons

-0.67

powder

-0.67

 marrow

-0.66

gom

-0.65

POSITIVE LOGITS

BILITY

1.02

 Tome

0.99

isa

0.94

pport

0.94

acs

0.93

uthor

0.92

BILITIES

0.85

qs

0.84

arta

0.83

Äį

0.80

Activations Density 0.017%

words related to the location or entity "Samisa"

the word "Isa" in various contexts throughout the document

No Comments

No Known Activations