INDEX

Explanations

names of actors and directors

oai_token-act-pair · gpt-3.5-turbo

names of actors and directors associated with films and television series

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

tnc

-0.77

dayName

-0.75

ickr

-0.73

è¦ļéĨĴ

-0.70

 rout

-0.68

thening

-0.68

ritis

-0.68

 subsistence

-0.67

åħī

-0.67

AAP

-0.67

POSITIVE LOGITS

 actor

1.10

 Whedon

1.07

 Vaughn

1.01

 Tarant

1.00

 actors

0.99

 Films

0.98

 actress

0.97

 Anderson

0.93

 Cage

0.93

 Shirley

0.91

Activations Density 0.278%

names of actors and directors

names of actors and directors associated with films and television series

No Comments

No Known Activations