INDEX

Explanations

proper nouns and terms related to different individuals and entities

oai_token-act-pair · gpt-3.5-turbo

mentions of characters or elements related to a specific narrative or storyline

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

SAY

-0.75

TERN

-0.74

acher

-0.73

 peanuts

-0.70

ependence

-0.65

IPM

-0.65

istant

-0.65

 almonds

-0.64

ãĥĨãĤ£

-0.63

cul

-0.63

POSITIVE LOGITS

lain

0.93

boat

0.93

anqu

0.74

lets

0.74

ilts

0.73

boats

0.72

loo

0.72

CK

0.72

glers

0.71

 Jenner

0.70

Activations Density 0.038%

proper nouns and terms related to different individuals and entities

mentions of characters or elements related to a specific narrative or storyline

No Comments

No Known Activations