INDEX

Explanations

references to a person or entity with the name "Ob" followed by a number representing the strength of activation

oai_token-act-pair · gpt-3.5-turbo

references to the word "Ob" or variations of it in various contexts

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

 Remastered

-0.81

 guiActiveUnfocused

-0.77

EngineDebug

-0.72

 Quadro

-0.68

 Carlson

-0.68

 Michaels

-0.67

WAYS

-0.67

rawdownloadcloneembedreportprint

-0.66

 Bree

-0.66

gas

-0.66

POSITIVE LOGITS

fusc

1.37

taining

1.28

lique

1.19

solete

1.19

lig

1.04

amacare

1.03

vious

1.00

noxious

1.00

oby

0.99

oro

0.98

Activations Density 0.008%

references to a person or entity with the name "Ob" followed by a number representing the strength of activation

references to the word "Ob" or variations of it in various contexts

No Comments

No Known Activations