INDEX

Explanations

terms related to text or messaging

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word 'text' and its variations in the document

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

vernment

-0.76

CVE

-0.73

deen

-0.72

CVE

-0.71

pload

-0.70

 Admission

-0.68

Ern

-0.68

lain

-0.68

Äĩ

-0.67

MAL

-0.65

POSITIVE LOGITS

ured

1.40

uality

1.07

uring

1.06

ures

1.05

plain

1.05

area

1.00

urized

1.00

ural

0.96

ual

0.93

 messages

0.92

Activations Density 0.029%

terms related to text or messaging

occurrences of the word 'text' and its variations in the document

No Comments

No Known Activations