INDEX

Explanations

terms related to the TV show "Game of Thrones"

oai_token-act-pair · gpt-3.5-turbo

references to the "Game of Thrones" series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iffe

-0.83

 staffed

-0.74

terday

-0.73

Downloadha

-0.73

ishable

-0.72

undai

-0.71

 chem

-0.69

rower

-0.69

irst

-0.68

 dotted

-0.68

POSITIVE LOGITS

cube

1.05

play

0.98

Maker

0.96

Spot

0.89

 Nerd

0.88

 Clash

0.86

pad

0.86

Cube

0.86

 Game

0.83

 Genie

0.82

Activations Density 0.021%

terms related to the TV show "Game of Thrones"

references to the "Game of Thrones" series

No Comments

No Known Activations