INDEX

Explanations

references to the immune system

oai_token-act-pair · gpt-4-turbo

terms related to the immune system and medical conditions involving the immune response

oai_token-act-pair · gpt-3.5-turbo

terms related to the immune system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

AU

-0.77

\\\\\\\\

-0.72

ousand

-0.71

âĢ¢âĢ¢

-0.71

 Roads

-0.70

mosp

-0.70

 Ange

-0.70

 Rasmussen

-0.69

ources

-0.69

 Newsp

-0.69

POSITIVE LOGITS

 immune

1.17

 immunity

0.93

immune

0.86

 defences

0.82

 defenses

0.78

 checkpoint

0.77

 immun

0.76

 thyroid

0.74

 suscept

0.74

 deficiency

0.72

Activations Density 0.013%

references to the immune system

terms related to the immune system and medical conditions involving the immune response

terms related to the immune system

No Comments

No Known Activations