INDEX

Explanations

something that happened on a specific day of the week in a particular location

oai_token-act-pair · gpt-3.5-turbo

references to specific nights of the week

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

cient

-0.70

UTF

-0.69

inter

-0.65

esp

-0.64

location

-0.64

annah

-0.63

atem

-0.63

ERY

-0.61

recated

-0.61

ignant

-0.61

POSITIVE LOGITS

night

0.82

 afternoon

0.75

 night

0.71

 onwards

0.67

 evening

0.65

opers

0.63

 UPDATE

0.63

 onward

0.63

nesday

0.62

fall

0.62

Activations Density 0.034%

something that happened on a specific day of the week in a particular location

references to specific nights of the week

No Comments

No Known Activations