INDEX

Explanations

direct quotations or citations

oai_token-act-pair · gpt-3.5-turbo

parenthetical statements and sections within the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 veget

-0.73

 invari

-0.73

 appropri

-0.72

 inund

-0.71

 virginity

-0.68

 cones

-0.67

 stud

-0.67

 appreci

-0.66

 erect

-0.66

 piping

-0.66

POSITIVE LOGITS

*)

1.35

Note

1.05

BOOK

1.04

click

1.04

MORE

1.04

-)

1.02

CNN

1.02

Reuters

1.01

Courtesy

1.00

+)

1.00

Activations Density 0.025%

direct quotations or citations

parenthetical statements and sections within the text

No Comments

No Known Activations