INDEX

Explanations

references to the body part 'lap'

oai_token-act-pair · gpt-3.5-turbo

references to "lap" 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

 Flavoring

-0.99

merce

-0.86

ãĥ¼ãĥĨãĤ£

-0.81

hips

-0.73

 Marketable

-0.72

EngineDebug

-0.71

 proport

-0.68

NESS

-0.68

 reconc

-0.67

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

-0.65

POSITIVE LOGITS

dogs

1.06

dog

0.94

ipop

0.94

Lap

0.94

ocobo

0.90

ois

0.85

ster

0.82

lap

0.81

sters

0.81

lap

0.80

Activations Density 0.013%

references to the body part 'lap'

references to "lap" in various contexts

No Comments

No Known Activations