INDEX

Explanations

dates written in a specific format

oai_token-act-pair · gpt-3.5-turbo

dates and chronological events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 glim

-0.78

pend

-0.65

 marqu

-0.65

sag

-0.62

uffer

-0.60

 enthus

-0.60

 corrid

-0.60

Redd

-0.59

 liber

-0.57

 sensations

-0.56

POSITIVE LOGITS

1.05

1.00

0.98

0.94

0.93

0.92

0.89

Activations Density 0.093%

dates written in a specific format

dates and chronological events

No Comments

No Known Activations