INDEX

Explanations

words related to inflammatory processes or situations

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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.89

llan

-0.83

DragonMagazine

-0.81

stood

-0.79

 Colleges

-0.79

 Teach

-0.75

BOOK

-0.74

 Scientists

-0.74

 Watching

-0.74

 Bastard

-0.73

POSITIVE LOGITS

orescence

1.25

 infl

1.04

ights

0.93

ations

0.91

oresc

0.91

ubric

0.86

atable

0.84

othal

0.82

oster

0.81

ating

0.80

Activations Density 0.006%

words related to inflammatory processes or situations

terms related to inflammation and its effects

No Comments

No Known Activations