INDEX

Explanations

phrases related to consideration or evaluation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consideration or evaluation of various subjects

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

ario

-0.74

sheets

-0.70

ixie

-0.65

--+

-0.64

 arrows

-0.63

 Meth

-0.63

Lear

-0.60

MAT

-0.60

angs

-0.59

erers

-0.59

POSITIVE LOGITS

tical

0.81

 precedent

0.69

 favorably

0.69

ilitarian

0.67

limits

0.67

jud

0.65

 unworthy

0.65

 judgment

0.65

priv

0.64

inventoryQuantity

0.63

Activations Density 0.147%

phrases related to consideration or evaluation

phrases indicating consideration or evaluation of various subjects

No Comments

No Known Activations