INDEX

Explanations

mentions of the TV show "Game of Thrones"

oai_token-act-pair · gpt-3.5-turbo

references to "Game" in various contexts, particularly "Game of Thrones."

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

sie

-0.77

undai

-0.75

 destro

-0.72

 staffed

-0.72

ylum

-0.71

iffe

-0.70

Downloadha

-0.70

 chem

-0.69

igham

-0.69

 politic

-0.69

POSITIVE LOGITS

cube

1.03

pad

0.99

play

0.97

Apps

0.89

 Game

0.87

zeb

0.86

Spot

0.85

wright

0.85

Cube

0.84

gage

0.83

Activations Density 0.018%

mentions of the TV show "Game of Thrones"

references to "Game" in various contexts, particularly "Game of Thrones."

No Comments

No Known Activations