INDEX

Explanations

words related to causality or sequence of events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "turn" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

è¦ļéĨĴ

-0.81

ainers

-0.71

capacity

-0.70

hered

-0.69

foundation

-0.68

aceous

-0.66

inately

-0.66

agan

-0.66

necess

-0.65

aph

-0.64

POSITIVE LOGITS

turn

0.81

edit

0.75

overs

0.72

coat

0.70

about

0.69

 turn

0.69

GW

0.68

undo

0.68

terday

0.65

Turn

0.64

Activations Density 0.034%

words related to causality or sequence of events

instances of the word "turn" in various contexts

No Comments

No Known Activations