INDEX

Explanations

the name "Kat" with different variations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Kat" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

interstitial

-0.78

dit

-0.76

lict

-0.68

istry

-0.64

uploads

-0.63

 relations

-0.63

acebook

-0.62

ername

-0.59

cffff

-0.58

 contraceptives

-0.58

POSITIVE LOGITS

rina

1.23

usha

1.07

anas

1.00

Kat

0.96

oton

0.94

kat

0.93

arine

0.90

agne

0.90

apult

0.89

apesh

0.88

Activations Density 0.036%

the name "Kat" with different variations

occurrences of the name "Kat" and its variations

No Comments

No Known Activations