INDEX

Explanations

details or specific information within the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "det" and its variations in different contexts

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

ocene

-0.91

manship

-0.81

ħĭ

-0.68

xual

-0.67

BSD

-0.66

 Awakens

-0.66

intendent

-0.65

 nomine

-0.64

NetMessage

-0.64

 beware

-0.64

POSITIVE LOGITS

ention

1.32

rans

1.17

achable

1.17

roit

1.13

ainer

1.09

ailed

1.06

rend

1.03

rit

1.01

rast

1.00

agon

0.97

Activations Density 0.017%

details or specific information within the text

instances of the word "det" and its variations in different contexts

No Comments

No Known Activations