INDEX

Explanations

names of actors and actresses

oai_token-act-pair · gpt-3.5-turbo

instances of the word "starring" and related terms indicating the presence of actors in films

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĵĺ

-0.84

foundation

-0.82

veland

-0.78

inventoryQuantity

-0.75

 propagate

-0.72

heit

-0.69

bred

-0.68

£ı

-0.67

abus

-0.66

pex

-0.65

POSITIVE LOGITS

leck

0.93

 starring

0.86

 Natalie

0.77

eele

0.76

Dust

0.73

 Shia

0.73

 Mickey

0.72

 actress

0.70

 Benedict

0.69

 Leonardo

0.68

Activations Density 0.047%

names of actors and actresses

instances of the word "starring" and related terms indicating the presence of actors in films

No Comments

No Known Activations