INDEX

Explanations

medical terms related to inflammation

oai_token-act-pair · gpt-3.5-turbo

terms related to inflammation and its effects

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

manship

-0.77

lish

-0.72

netic

-0.72

leness

-0.71

ilian

-0.70

LY

-0.70

LI

-0.69

NESS

-0.69

sonian

-0.68

ILY

-0.68

POSITIVE LOGITS

ating

1.60

ators

1.47

atable

1.31

ates

1.30

orescence

1.25

ator

1.21

ater

1.21

ated

1.19

aters

1.18

ations

1.16

Activations Density 0.056%

medical terms related to inflammation

terms related to inflammation and its effects

No Comments

No Known Activations