INDEX

Explanations

instances where objects are found or located in a particular place or context

oai_token-act-pair · gpt-3.5-turbo

the preposition 'in' used frequently throughout the text

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

llor

-0.73

LOG

-0.71

fters

-0.68

=]

-0.68

CLASSIFIED

-0.67

HAEL

-0.65

lement

-0.64

ZA

-0.64

catentry

-0.64

phans

-0.63

POSITIVE LOGITS

 lieu

1.25

clusions

1.16

 accordance

1.16

 conjunction

1.12

 relation

1.08

versions

1.05

ordinate

1.05

 vitro

1.05

effic

1.04

roads

1.03

Activations Density 0.457%

instances where objects are found or located in a particular place or context

the preposition 'in' used frequently throughout the text

No Comments

No Known Activations