INDEX

Explanations

references to movies and TV shows

oai_token-act-pair · gpt-3.5-turbo

film genres and their respective characteristics

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

Aid

-0.83

aples

-0.76

hiba

-0.73

Dat

-0.70

quist

-0.70

²¾

-0.67

foundation

-0.65

MpServer

-0.65

gencies

-0.65

ciating

-0.64

POSITIVE LOGITS

 starring

1.11

 sequel

1.08

 adaptation

1.01

 thriller

0.98

 Artemis

0.95

 Dracula

0.94

 trilogy

0.94

 titled

0.88

 theaters

0.87

 sequels

0.86

Activations Density 0.242%

references to movies and TV shows

film genres and their respective characteristics

No Comments

No Known Activations