INDEX

Explanations

the abbreviation "OU" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term related to the concept of 'output'

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

ãĤ¹ãĥĪ

-0.78

ãĥŁ

-0.75

ãĥ¼ãĥĨãĤ£

-0.69

 Cobra

-0.68

ãĥĵ

-0.67

ãĤº

-0.66

ãĤ¢ãĥ«

-0.66

 Kraken

-0.66

ãĥķãĤ©

-0.65

 Birch

-0.64

POSITIVE LOGITS

BLE

1.02

PDATE

0.98

LET

0.92

OTUS

0.89

TERN

0.88

ser

0.85

lisher

0.85

terness

0.85

VEN

0.85

UU

0.83

Activations Density 0.009%

the abbreviation "OU" in various contexts

occurrences of the term related to the concept of 'output'

No Comments

No Known Activations