INDEX

Explanations

phrases related to environmental disasters and pollution

oai_token-act-pair · gpt-3.5-turbo

phrases indicating sources or origins of substances or phenomena

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olson

-0.92

merce

-0.82

vet

-0.79

äºĶ

-0.77

ierrez

-0.75

ratulations

-0.73

ãĤ³

-0.73

quote

-0.73

hirt

-0.72

TEXT

-0.72

POSITIVE LOGITS

 afar

1.35

 inside

0.88

 whence

0.84

 abroad

0.79

 beneath

0.79

 atop

0.78

 Fukushima

0.76

 outside

0.76

 underneath

0.76

 scratch

0.76

Activations Density 0.153%

phrases related to environmental disasters and pollution

phrases indicating sources or origins of substances or phenomena

No Comments

No Known Activations