INDEX

Explanations

terms related to disagreement or conflict

oai_token-act-pair · gpt-3.5-turbo

terms related to dissociation and identity issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

glers

-0.74

 Elves

-0.73

çĦ

-0.73

 Werewolf

-0.71

 Ivory

-0.69

 Mongolia

-0.66

 Kinnikuman

-0.66

 Inspector

-0.65

 Archdemon

-0.65

 stakes

-0.64

POSITIVE LOGITS

imilar

1.42

ociation

1.41

ipation

1.37

ociated

1.31

oci

1.29

ension

1.26

ident

1.24

olving

1.24

ertation

1.22

ociate

1.09

Activations Density 0.018%

terms related to disagreement or conflict

terms related to dissociation and identity issues

No Comments

No Known Activations