INDEX

Explanations

questions starting with "Who"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Who"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MER

-0.78

PORT

-0.67

 Pilgrim

-0.63

 Hyde

-0.62

mun

-0.58

outer

-0.58

 compatibility

-0.57

 readiness

-0.57

 relaxation

-0.57

rog

-0.56

POSITIVE LOGITS

soever

1.24

ever

1.09

oping

1.05

abouts

1.03

 else

0.97

 cares

0.96

oped

0.91

 knows

0.90

ileaks

0.80

 cared

0.79

Activations Density 0.092%

questions starting with "Who"

instances of the word "Who"

No Comments

No Known Activations