INDEX

Explanations

phrases related to specific effects or phenomena

oai_token-act-pair · gpt-3.5-turbo

references to various "effects" or phenomena described in social or psychological contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pigeon

-0.72

mbuds

-0.65

 Methodist

-0.65

zar

-0.63

 Timber

-0.63

 Kats

-0.60

 rooft

-0.60

 Standards

-0.60

 quarters

-0.59

Dud

-0.59

POSITIVE LOGITS

iveness

1.21

uated

1.16

ual

1.11

uating

1.05

ually

1.05

ively

1.04

uel

0.98

uate

0.98

bringer

0.98

uality

0.97

Activations Density 0.034%

phrases related to specific effects or phenomena

references to various "effects" or phenomena described in social or psychological contexts

No Comments

No Known Activations