INDEX

Explanations

phrases and terms related to the works of J.R.R. Tolkien, such as characters, settings, and plot elements

oai_token-act-pair · gpt-3.5-turbo

references to J.R.R. Tolkien and his works

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

aminer

-0.84

icio

-0.76

Ĩ

-0.70

âĸ¬

-0.70

Ŀ

-0.69

anooga

-0.69

achusetts

-0.67

ivated

-0.67

 chef

-0.66

urized

-0.66

POSITIVE LOGITS

olkien

1.30

 Tolkien

1.21

 Gand

0.97

 Hobbit

0.94

sson

0.86

kj

0.84

agnar

0.82

 Bagg

0.81

 Trave

0.81

forth

0.75

Activations Density 0.035%

phrases and terms related to the works of J.R.R. Tolkien, such as characters, settings, and plot elements

references to J.R.R. Tolkien and his works

No Comments

No Known Activations