INDEX

Explanations

words related to a person named "Tre"

oai_token-act-pair · gpt-3.5-turbo

the name "Tre" along with its variations and mentions

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

 Parenthood

-0.76

enegger

-0.67

ISO

-0.62

 Gujar

-0.61

 Naomi

-0.60

INESS

-0.60

 Kirin

-0.60

ulators

-0.59

 Bangalore

-0.58

 polarized

-0.58

POSITIVE LOGITS

asury

1.10

asures

1.09

pez

1.01

acher

0.99

asure

0.98

ngth

0.96

uner

0.96

gment

0.94

nder

0.94

llo

0.93

Activations Density 0.015%

words related to a person named "Tre"

the name "Tre" along with its variations and mentions

No Comments

No Known Activations