INDEX

Explanations

words related to daily life activities or occurrences

oai_token-act-pair · gpt-3.5-turbo

references to daily routines and common experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aye

-0.88

owitz

-0.86

essee

-0.86

zik

-0.80

bid

-0.80

ramids

-0.78

egal

-0.75

atorial

-0.74

atchewan

-0.74

dinand

-0.73

POSITIVE LOGITS

motion

0.98

 everyday

0.90

 Everyday

0.89

 occurrence

0.85

 life

0.85

 occurrences

0.84

 necessities

0.79

time

0.76

 waking

0.75

 routine

0.75

Activations Density 0.015%

words related to daily life activities or occurrences

references to daily routines and common experiences

No Comments

No Known Activations