INDEX

Explanations

mentions of animated content or animation-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to animation and animated characters

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

etheless

-0.71

peak

-0.70

holder

-0.65

 Roses

-0.64

 Byrd

-0.63

 expectancy

-0.63

stood

-0.63

 mark

-0.63

 Hurricanes

-0.62

 Patient

-0.60

POSITIVE LOGITS

agus

1.20

agi

1.13

ator

1.09

oji

1.06

ators

1.06

itives

0.96

ating

0.95

ations

0.94

antine

0.93

osity

0.93

Activations Density 0.009%

mentions of animated content or animation-related terms

terms related to animation and animated characters

No Comments

No Known Activations