INDEX

Explanations

dates and historical events

oai_token-act-pair · gpt-3.5-turbo

instances of numerical data or dates mentioned in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

¬¼

-0.77

reated

-0.70

iri

-0.66

cius

-0.66

irc

-0.65

 heterogeneity

-0.64

iculty

-0.63

ire

-0.62

eries

-0.62

robe

-0.61

POSITIVE LOGITS

when

1.14

 when

0.99

 according

0.94

 shortly

0.92

 although

0.89

 leaving

0.86

according

0.84

 coinc

0.83

 prompting

0.82

 culminating

0.82

Activations Density 0.235%

dates and historical events

instances of numerical data or dates mentioned in a text

No Comments

No Known Activations