INDEX

Explanations

expressions related to periods of time such as "every year" or "each year"

oai_token-act-pair · gpt-3.5-turbo

references to annual events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ociate

-0.81

tymology

-0.77

MpServer

-0.72

bent

-0.71

aleb

-0.68

agra

-0.67

ymm

-0.66

jri

-0.66

artisan

-0.66

emort

-0.65

POSITIVE LOGITS

 thereafter

1.05

 throughout

0.83

lins

0.83

night

0.79

 until

0.77

Iw

0.70

 except

0.68

until

0.66

 basis

0.65

 whenever

0.63

Activations Density 0.077%

expressions related to periods of time such as "every year" or "each year"

references to annual events or occurrences

No Comments

No Known Activations