INDEX

Explanations

words related to a specific location or place

oai_token-act-pair · gpt-3.5-turbo

instances of the term "ap" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Monstrous

-0.70

 phyl

-0.64

 explan

-0.64

 horizont

-0.62

 interf

-0.60

 defic

-0.59

 disapp

-0.59

 exha

-0.58

 Schwarzenegger

-0.58

ccording

-0.57

POSITIVE LOGITS

olitan

1.41

oleon

1.38

ocalypse

1.19

ropri

1.17

ocalyptic

1.11

edia

1.09

rison

1.07

olitics

1.06

onent

1.05

olicy

0.99

Activations Density 0.047%

words related to a specific location or place

instances of the term "ap" in various contexts

No Comments

No Known Activations