INDEX

Explanations

phrases related to being caused or driven by something

oai_token-act-pair · gpt-3.5-turbo

terms that describe causes or driving factors behind events or changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

atform

-0.60

 Canad

-0.58

framework

-0.58

HAHAHAHA

-0.53

 TYPE

-0.52

assies

-0.51

antage

-0.51

 DRAGON

-0.51

ahi

-0.51

 traged

-0.51

POSITIVE LOGITS

by

1.40

by

1.13

 partly

1.05

By

1.01

 chiefly

0.97

 principally

0.97

BY

0.96

 largely

0.95

 primarily

0.94

By

0.92

Activations Density 0.118%

phrases related to being caused or driven by something

terms that describe causes or driving factors behind events or changes

No Comments

No Known Activations