INDEX

Explanations

pronouns followed by possessive pronouns

oai_token-act-pair · gpt-3.5-turbo

pronouns in plural or possessive forms

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

ĸļ

-0.68

fill

-0.67

 Walters

-0.66

Cu

-0.66

Grey

-0.65

usa

-0.65

mire

-0.65

vine

-0.64

Sn

-0.64

parser

-0.64

POSITIVE LOGITS

own

1.71

 entire

1.11

 reputation

1.01

 fortunes

1.00

selves

0.97

 allegiance

0.96

 rightful

0.94

 knees

0.93

 arms

0.92

 vision

0.91

Activations Density 0.244%

pronouns followed by possessive pronouns

pronouns in plural or possessive forms

No Comments

No Known Activations