INDEX

Explanations

medical and technical terms

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to important concepts or terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 guiActiveUnfocused

-0.75

 Cthulhu

-0.72

 Akin

-0.71

 Hutchinson

-0.70

 Mara

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.68

 mast

-0.68

 misunder

-0.66

 Sheen

-0.65

 mistaken

-0.65

POSITIVE LOGITS

uments

1.04

ridges

1.04

ition

1.03

ument

0.99

ances

0.98

ices

0.98

ners

0.97

ensions

0.97

ants

0.96

ctions

0.95

Activations Density 0.185%

medical and technical terms

abbreviations and acronyms related to important concepts or terms

No Comments

No Known Activations