INDEX

Explanations

phrases related to thoughts or perceptions, often with a focus on certainty or importance

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "to be" or its forms in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

umbnails

-0.76

andise

-0.72

frames

-0.71

ADS

-0.71

Frames

-0.68

asers

-0.67

atre

-0.67

itcher

-0.67

éĹĺ

-0.67

è¦ļéĨĴ

-0.66

POSITIVE LOGITS

 raining

1.05

 impossible

1.04

 happening

1.01

 easier

0.90

 easy

0.87

 meant

0.85

 possible

0.85

 worthwhile

0.84

 gonna

0.83

 futile

0.81

Activations Density 0.233%

phrases related to thoughts or perceptions, often with a focus on certainty or importance

instances of the verb "to be" or its forms in various contexts

No Comments

No Known Activations