INDEX

Explanations

references to the name "Irving"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Irving."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Laun

-0.81

soDeliveryDate

-0.78

 Elephant

-0.72

estone

-0.71

hare

-0.70

achine

-0.70

user

-0.69

hya

-0.68

ombat

-0.66

 Elys

-0.65

POSITIVE LOGITS

 Irving

0.81

 Hayward

0.79

 IMAGES

0.77

 Gork

0.71

bart

0.66

Fug

0.63

Cub

0.63

abad

0.63

IFA

0.62

bid

0.62

Activations Density 0.066%

references to the name "Irving"

references to the name "Irving."

No Comments

No Known Activations