INDEX

Explanations

phrases indicating future events or actions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate future events or actions

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

 foresee

-0.73

 Princ

-0.65

 constit

-0.63

orsi

-0.63

 fearing

-0.62

 anticipating

-0.62

annot

-0.62

 thereto

-0.60

Reporting

-0.60

ials

-0.59

POSITIVE LOGITS

hin

0.80

nova

0.79

å§«

0.77

morrow

0.75

 tomorrow

0.72

arbon

0.71

rill

0.68

acea

0.68

vana

0.65

ãĤ¼ãĤ¦ãĤ¹

0.65

Activations Density 0.140%

phrases indicating future events or actions

phrases that indicate future events or actions

No Comments

No Known Activations