INDEX

Explanations

words related to the immune system

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 @ 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

\\\\\\\\

-0.81

ivia

-0.79

 Paper

-0.71

*/(

-0.71

 Mond

-0.70

hare

-0.69

AU

-0.69

ilts

-0.66

google

-0.66

 Rasmussen

-0.64

POSITIVE LOGITS

mediated

0.87

 glob

0.85

 immune

0.82

ogen

0.78

 infiltrate

0.76

 deficiency

0.76

ogens

0.75

ogl

0.73

obl

0.72

 gland

0.71

Activations Density 0.033%

words related to the immune system

terms related to the immune system

No Comments

No Known Activations