INDEX

Explanations

time-related events using the word 'until'

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time-related conditions or sequences

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

ociate

-0.84

 plurality

-0.64

 guiIcon

-0.64

 tolerate

-0.64

 spin

-0.63

 cellar

-0.63

bors

-0.62

inguished

-0.62

ÃŃa

-0.61

 mishand

-0.61

POSITIVE LOGITS

rance

0.91

uez

0.72

 disapp

0.66

amaz

0.65

Eug

0.64

 dstg

0.64

FUL

0.63

ENTS

0.60

ãĥ¤

0.60

agn

0.60

Activations Density 0.232%

time-related events using the word 'until'

phrases indicating time-related conditions or sequences

No Comments

No Known Activations