INDEX

Explanations

phrases mentioning trilogies

oai_token-act-pair · gpt-3.5-turbo

references to trilogies and series in media

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

regulated

-0.69

anged

-0.69

bats

-0.67

arov

-0.66

laws

-0.66

anim

-0.66

animous

-0.66

places

-0.66

animate

-0.65

esting

-0.64

POSITIVE LOGITS

 trilogy

1.19

 Trilogy

1.02

çīĪ

0.79

ilogy

0.79

 Afric

0.78

ttes

0.78

 RELE

0.76

peat

0.73

 sequels

0.73

 adolesc

0.73

Activations Density 0.011%

phrases mentioning trilogies

references to trilogies and series in media

No Comments

No Known Activations