INDEX

Explanations

phrases containing the word "closed"

oai_token-act-pair · gpt-3.5-turbo

references to closed or private settings and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

nesota

-0.75

andum

-0.73

 Metatron

-0.73

aire

-0.73

nik

-0.72

ãĥīãĥ©ãĤ´ãĥ³

-0.72

arya

-0.72

IVE

-0.71

intend

-0.69

iage

-0.68

POSITIVE LOGITS

 doors

0.87

 throttle

0.75

 loopholes

0.74

 shutter

0.74

tering

0.72

 Doors

0.72

 door

0.71

lid

0.71

 gates

0.71

 down

0.70

Activations Density 0.018%

phrases containing the word "closed"

references to closed or private settings and events

No Comments

No Known Activations