INDEX

Explanations

keywords related to the term "Trinity."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Trinity" and variations related to it

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

acco

-0.78

ilage

-0.75

estern

-0.73

UGE

-0.70

hard

-0.68

ARDS

-0.68

insula

-0.67

urations

-0.67

bers

-0.66

ARD

-0.64

POSITIVE LOGITS

inity

0.92

 Trinity

0.88

idad

0.77

ivari

0.76

 Lutheran

0.75

Tree

0.69

idental

0.69

 Divinity

0.68

 Leilan

0.68

uality

0.68

Activations Density 0.015%

keywords related to the term "Trinity."

occurrences of the word "Trinity" and variations related to it

No Comments

No Known Activations