INDEX

Explanations

sentences ending with a strong or emphatic statement

oai_token-act-pair · gpt-3.5-turbo

instances of the word "no" and associated negation contexts

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

gypt

-0.70

ounded

-0.68

mud

-0.66

ounds

-0.65

abal

-0.64

tro

-0.62

oufl

-0.61

arthy

-0.61

MpServer

-0.61

etitive

-0.61

POSITIVE LOGITS

sir

0.97

nor

0.75

 thank

0.71

æĪ

0.71

onsense

0.69

 kidding

0.67

nor

0.67

 whatsoever

0.65

Shift

0.64

 dear

0.64

Activations Density 0.055%

sentences ending with a strong or emphatic statement

instances of the word "no" and associated negation contexts

No Comments

No Known Activations