INDEX

Explanations

medical conditions and terms related to technology and politics

oai_token-act-pair · gpt-3.5-turbo

nouns and proper nouns associated with brands and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 ..."

-0.81

>]

-0.60

 ....

-0.55

}.

-0.53

 anymore

-0.53

 shoulder

-0.52

ãģ¾

-0.51

],

-0.51

 haha

-0.51

 dividing

-0.51

POSITIVE LOGITS

ensibly

0.76

anyahu

0.70

hester

0.70

ashtra

0.68

ulhu

0.64

raltar

0.63

udos

0.62

iasis

0.62

unia

0.61

roma

0.61

Activations Density 0.503%

medical conditions and terms related to technology and politics

nouns and proper nouns associated with brands and products

No Comments

No Known Activations