INDEX

Explanations

terms related to radioactivity

oai_token-act-pair · gpt-3.5-turbo

words related to radioactivity and alcohol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alter

-0.80

wright

-0.77

plin

-0.76

ploma

-0.72

chair

-0.72

changed

-0.71

hm

-0.71

cham

-0.71

ador

-0.71

zig

-0.70

POSITIVE LOGITS

 substances

1.04

NESS

0.97

 foods

0.85

 fruits

0.84

 goods

0.83

 fruit

0.82

 contents

0.81

 vegetables

0.81

 properties

0.80

 vegetable

0.79

Activations Density 0.082%

terms related to radioactivity

words related to radioactivity and alcohol

No Comments

No Known Activations