INDEX

Explanations

phrases related to identifying people, things, or locations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate identifying people, places, or things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

otiation

-0.87

ĸļ

-0.77

emn

-0.75

renheit

-0.75

VERTISEMENT

-0.74

ulo

-0.70

powered

-0.68

ulation

-0.68

 reckoning

-0.67

fortune

-0.67

POSITIVE LOGITS

 culprit

1.71

 weaknesses

1.18

 perpetrators

1.12

 vulnerabilities

1.10

 flaws

1.10

 defects

1.03

 offending

1.03

 source

1.03

 problematic

1.03

 perpetrator

1.03

Activations Density 0.342%

phrases related to identifying people, things, or locations

phrases that indicate identifying people, places, or things

No Comments

No Known Activations