INDEX

Explanations

words related to days of the week and activities/events occurring on those days

oai_token-act-pair · gpt-3.5-turbo

possessive forms related to time or events

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

alties

-0.79

ographically

-0.72

wit

-0.72

then

-0.71

washed

-0.70

rust

-0.69

vae

-0.67

avering

-0.67

heit

-0.67

don

-0.67

POSITIVE LOGITS

 announcement

0.89

 morning

0.82

 arrival

0.81

 deadline

0.80

 edition

0.77

 afternoon

0.76

 biggest

0.74

 anniversary

0.74

 unveiling

0.73

 evening

0.72

Activations Density 0.038%

words related to days of the week and activities/events occurring on those days

possessive forms related to time or events

No Comments

No Known Activations