INDEX

Explanations

actions or scenarios involving disruption or disruptive activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "disrupt" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rera

-0.74

abet

-0.68

ramid

-0.65

phans

-0.64

aternity

-0.63

Cay

-0.62

onz

-0.62

hl

-0.62

arenthood

-0.62

True

-0.61

POSITIVE LOGITS

 disrupt

1.16

 disruptions

1.01

 disrupting

1.01

 disruption

1.00

 disrupted

1.00

 disruptive

0.99

 havoc

0.94

alore

0.92

 cannabin

0.77

iversal

0.76

Activations Density 0.009%

actions or scenarios involving disruption or disruptive activities

instances of the word "disrupt" and its variations

No Comments

No Known Activations