INDEX

Explanations

terms related to personal identification, such as names and other personal information

oai_token-act-pair · gpt-3.5-turbo

references to personal identification details and their usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vable

-0.79

grade

-0.79

ractical

-0.77

issions

-0.76

worms

-0.75

 stalls

-0.74

MRI

-0.73

issance

-0.73

heim

-0.69

urious

-0.69

POSITIVE LOGITS

 initials

0.98

 nationality

0.85

 pronouns

0.85

 trademarks

0.80

è£

0.80

 surname

0.78

 suffix

0.76

 likeness

0.76

 pronoun

0.75

 redacted

0.73

Activations Density 0.371%

terms related to personal identification, such as names and other personal information

references to personal identification details and their usage

No Comments

No Known Activations