INDEX

Explanations

pronouns followed by a possessive pronoun and a verb, indicating actions related to possession and relationships

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals and personal pronouns

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

ãĥĲ

-0.81

ĸļ

-0.79

ieri

-0.76

hesda

-0.69

idelines

-0.69

iquette

-0.64

izzard

-0.63

inance

-0.62

omial

-0.62

antle

-0.61

POSITIVE LOGITS

 nightmares

0.91

 senses

0.88

 classmates

0.80

 imag

0.79

 imagining

0.78

 guess

0.78

 doubts

0.78

 witnessed

0.77

 awoke

0.76

 watched

0.75

Activations Density 0.837%

pronouns followed by a possessive pronoun and a verb, indicating actions related to possession and relationships

references to specific individuals and personal pronouns

No Comments

No Known Activations