INDEX

Explanations

instances of time periods, especially those of extended duration

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing actions or situations over time

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

iru

-0.82

inki

-0.74

 kicker

-0.61

ppa

-0.60

reat

-0.59

onics

-0.59

Accessory

-0.58

 Kills

-0.57

Sky

-0.57

-0.56

POSITIVE LOGITS

 lately

1.20

 since

1.05

since

0.91

 awhile

0.76

 previously

0.70

 unsuccessfully

0.70

 previous

0.68

 decades

0.65

 past

0.65

 recently

0.65

Activations Density 0.571%

instances of time periods, especially those of extended duration

phrases indicating ongoing actions or situations over time

No Comments

No Known Activations