INDEX

Explanations

phrases indicating a duration of time

oai_token-act-pair · gpt-3.5-turbo

references to units of time, specifically the word "years"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

inki

-0.85

hao

-0.80

emort

-0.76

egu

-0.75

vana

-0.72

avier

-0.68

ragon

-0.65

ashing

-0.64

ella

-0.63

notice

-0.62

POSITIVE LOGITS

ago

0.94

now

0.93

 thereafter

0.90

 afterward

0.86

 afterwards

0.76

 observers

0.73

Ago

0.71

 pundits

0.71

 commentators

0.68

 prior

0.67

Activations Density 0.074%

phrases indicating a duration of time

references to units of time, specifically the word "years"

No Comments

No Known Activations