INDEX

Explanations

phrases related to commissions or specific tasks/issues given by authorities

oai_token-act-pair · gpt-3.5-turbo

the word "mission" 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 @ 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

APD

-0.72

accompan

-0.72

rises

-0.70

aws

-0.65

cially

-0.65

OC

-0.62

 IMAGES

-0.62

 cannabinoid

-0.59

heast

-0.59

 molecules

-0.58

POSITIVE LOGITS

mission

1.11

ission

0.84

issions

0.80

ISSION

0.80

phis

0.79

orship

0.77

iotic

0.76

atorium

0.76

naires

0.75

illery

0.75

Activations Density 0.014%

phrases related to commissions or specific tasks/issues given by authorities

the word "mission" and its variations

No Comments

No Known Activations