INDEX

Explanations

terms related to the immune system and autoimmune conditions

oai_token-act-pair · gpt-3.5-turbo

references to the immune system and its functions

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

 Rasmussen

-0.79

\\\\\\\\

-0.79

-0.75

hare

-0.75

AU

-0.72

google

-0.72

âĢ¢âĢ¢

-0.72

ousand

-0.72

ABE

-0.69

ichen

-0.69

POSITIVE LOGITS

 immune

1.09

 immunity

0.92

mediated

0.84

 defences

0.83

 glob

0.80

immune

0.79

 deficiency

0.79

 defenses

0.78

 suscept

0.75

 reaction

0.73

Activations Density 0.010%

terms related to the immune system and autoimmune conditions

references to the immune system and its functions

No Comments

No Known Activations