INDEX

Explanations

interactions or relationships between different elements or entities

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "inter-" indicating interconnectedness or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

FUL

-0.64

 Chaser

-0.63

aughs

-0.63

DragonMagazine

-0.62

 credentials

-0.61

IELD

-0.60

Magikarp

-0.60

wagen

-0.60

hyde

-0.59

 accelerated

-0.57

POSITIVE LOGITS

lude

1.16

racial

1.07

locking

1.04

continental

1.03

dimensional

1.00

disciplinary

0.99

stitial

0.98

mitt

0.97

cession

0.96

loc

0.95

Activations Density 0.015%

interactions or relationships between different elements or entities

instances of the prefix "inter-" indicating interconnectedness or relationships

No Comments

No Known Activations