INDEX

Explanations

personal pronouns followed by verbs indicating actions the pronoun is taking

oai_token-act-pair · gpt-3.5-turbo

first-person and second-person pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ious

-0.69

liest

-0.66

angering

-0.65

inery

-0.65

natal

-0.64

lihood

-0.63

agement

-0.61

 Archdemon

-0.60

imon

-0.60

scription

-0.59

POSITIVE LOGITS

 goes

0.79

go

0.75

eps

0.74

 again

0.67

 sits

0.64

comes

0.64

 stands

0.63

 belong

0.63

go

0.62

 went

0.62

Activations Density 0.072%

personal pronouns followed by verbs indicating actions the pronoun is taking

first-person and second-person pronouns

No Comments

No Known Activations