INDEX

Explanations

words related to spinning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spinning" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Territories

-0.76

eq

-0.72

 Ancients

-0.69

hetical

-0.67

orers

-0.67

abet

-0.66

orate

-0.66

uters

-0.65

avez

-0.64

ylum

-0.64

POSITIVE LOGITS

 spinning

1.25

 spin

1.15

 spins

1.14

 spun

1.11

 yarn

0.97

 slic

0.93

 tremend

0.91

 weaving

0.89

ners

0.87

 weave

0.86

Activations Density 0.013%

words related to spinning

instances of the word "spinning" and its variations

No Comments

No Known Activations