INDEX

Explanations

the word "whole" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to significant concepts, entities, or phenomena described in a broad context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 occasional

-0.70

favorite

-0.64

 affinity

-0.58

 Prel

-0.57

odan

-0.56

 Samar

-0.56

trak

-0.56

nery

-0.55

 Runner

-0.55

eka

-0.55

POSITIVE LOGITS

 except

0.84

ä»£

0.82

ãĤ¼ãĤ¦ãĤ¹

0.79

 Including

0.71

äºĶ

0.71

Tes

0.70

 revolves

0.70

âĶĢâĶĢ

0.70

 imaginable

0.69

Registered

0.69

Activations Density 0.142%

the word "whole" in various contexts

references to significant concepts, entities, or phenomena described in a broad context

No Comments

No Known Activations