INDEX

Explanations

terms related to the immune system and immune response

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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

hare

-0.91

ABE

-0.75

YC

-0.72

 Cars

-0.71

 Woodward

-0.70

anu

-0.69

 Pound

-0.68

AU

-0.67

ivia

-0.67

OU

-0.66

POSITIVE LOGITS

 glob

1.06

 system

1.03

 glands

0.97

 response

0.94

 systems

0.91

 defenses

0.89

 deficiency

0.89

 infiltrate

0.88

 suppression

0.88

 gland

0.88

Activations Density 0.051%

terms related to the immune system and immune response

references to the immune system and its functions

No Comments

No Known Activations