INDEX

Explanations

phrases indicating similarity or sameness

oai_token-act-pair · gpt-3.5-turbo

repeated references to the concept of sameness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ases

-0.80

*=-

-0.76

åĪ

-0.71

uria

-0.67

gets

-0.67

rosso

-0.67

airs

-0.66

HI

-0.65

rection

-0.65

 Provided

-0.65

POSITIVE LOGITS

 thing

0.96

 exact

0.86

ol

0.76

 amount

0.71

 ballpark

0.71

iating

0.70

 everywhere

0.70

worldly

0.69

 kind

0.67

 playbook

0.67

Activations Density 0.036%

phrases indicating similarity or sameness

repeated references to the concept of sameness

No Comments

No Known Activations