INDEX

Explanations

terms related to the immune system and immune responses

oai_token-act-pair · gpt-3.5-turbo

references to the immune system and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

\\\\\\\\

-0.87

-0.82

 Rasmussen

-0.76

ivia

-0.76

ABE

-0.75

*/(

-0.74

 McGee

-0.73

holder

-0.70

 Paper

-0.69

google

-0.68

POSITIVE LOGITS

 immune

0.92

 glob

0.89

 defences

0.83

mediated

0.82

 defenses

0.80

 deficiency

0.78

 tract

0.76

 immunity

0.75

 infiltrate

0.74

 response

0.73

Activations Density 0.016%

terms related to the immune system and immune responses

references to the immune system and related concepts

No Comments

No Known Activations