INDEX

Explanations

references to achievements or results in various areas such as competitions, research, or testing

oai_token-act-pair · gpt-3.5-turbo

references to notable achievements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

abo

-0.64

 skelet

-0.64

earch

-0.62

onica

-0.62

ionage

-0.62

ugs

-0.61

.")

-0.61

rolet

-0.60

assad

-0.59

arger

-0.59

POSITIVE LOGITS

Âł

0.83

↵Âł

0.78

 Âł

0.75

 [âĢ¦]

0.75

 whilst

0.64

 Âł Âł Âł Âł

0.63

 ....

0.60

 Âł Âł

0.60

Firstly

0.59

 âĢİ

0.58

Activations Density 2.117%

references to achievements or results in various areas such as competitions, research, or testing

references to notable achievements or statistics

No Comments

No Known Activations