INDEX

Explanations

phrases related to the X-Men

oai_token-act-pair · gpt-3.5-turbo

references to specific comic book properties or 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

Cla

-0.71

ktop

-0.68

ieri

-0.67

 quitting

-0.66

kson

-0.65

 "$:/

-0.65

 pract

-0.63

 TODAY

-0.63

DERR

-0.63

 digestion

-0.63

POSITIVE LOGITS

shaped

1.05

sized

0.97

powered

0.96

tra

0.95

factor

0.92

collar

0.91

dimensional

0.91

series

0.90

linked

0.90

level

0.88

Activations Density 0.113%

phrases related to the X-Men

references to specific comic book properties or characters

No Comments

No Known Activations