INDEX

Explanations

mentions of specific locations

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" appearing 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.69

CLASSIFIED

-0.65

bryce

-0.60

 contag

-0.58

catentry

-0.58

 convol

-0.57

 showc

-0.57

NOW

-0.57

 disapp

-0.56

channelAvailability

-0.54

POSITIVE LOGITS

 lieu

1.22

 accordance

1.14

ordinate

1.13

clus

1.12

 conjunction

1.09

patient

1.06

clusions

1.05

roads

1.03

animate

1.02

 vitro

1.00

Activations Density 0.779%

mentions of specific locations

the preposition "in" appearing frequently throughout the text

No Comments

No Known Activations