INDEX

Explanations

dates, especially the month and year

oai_token-act-pair · gpt-3.5-turbo

dates, specifically in the format of months and years

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cot

-0.77

 ausp

-0.72

soDeliveryDate

-0.72

rikes

-0.70

kef

-0.70

esc

-0.69

emetery

-0.63

ynes

-0.63

yip

-0.63

cised

-0.62

POSITIVE LOGITS

ÙĨ

0.77

Ability

0.64

Ø¯

0.62

ulia

0.61

 correctness

0.61

ÙĦ

0.60

acity

0.59

 Data

0.58

 Redmond

0.57

Øª

0.56

Activations Density 0.049%

dates, especially the month and year

dates, specifically in the format of months and years

No Comments

No Known Activations