INDEX

Explanations

words related to chronological time markers, specifically years and months

oai_token-act-pair · gpt-3.5-turbo

references to time durations and ages

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hip

-0.83

 Scrib

-0.75

ufficient

-0.71

terday

-0.68

hov

-0.67

 Drawn

-0.66

ourcing

-0.66

aukee

-0.65

ides

-0.65

 Haram

-0.65

POSITIVE LOGITS

 olds

1.15

 lengths

0.76

 platinum

0.72

old

0.67

iversary

0.66

 lockdown

0.64

 increments

0.64

 experien

0.62

 beast

0.61

hz

0.61

Activations Density 0.077%

words related to chronological time markers, specifically years and months

references to time durations and ages

No Comments

No Known Activations