INDEX

Explanations

words related to the concept of a future event or something about to happen

oai_token-act-pair · gpt-3.5-turbo

references to visual boundaries or limits

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hiro

-0.82

NetMessage

-0.80

UGC

-0.73

aud

-0.71

hib

-0.71

ymph

-0.70

ongyang

-0.70

GB

-0.69

ough

-0.68

ERC

-0.68

POSITIVE LOGITS

 horizon

1.30

izons

1.18

naire

0.76

wip

0.76

izon

0.76

 lobe

0.74

geist

0.72

 hawk

0.71

 ledge

0.71

 vortex

0.68

Activations Density 0.004%

words related to the concept of a future event or something about to happen

references to visual boundaries or limits

No Comments

No Known Activations