INDEX

Explanations

phrases related to interviews

oai_token-act-pair · gpt-3.5-turbo

references to interviews

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

math

-0.72

 rejoice

-0.67

mil

-0.64

blue

-0.63

 consolation

-0.62

borgh

-0.61

ModLoader

-0.61

jri

-0.61

hover

-0.61

ciplinary

-0.61

POSITIVE LOGITS

ees

1.34

ee

1.05

 transcripts

1.01

 interviews

0.99

 conducted

0.98

 interview

0.98

 Transcript

0.91

 subjects

0.89

ioned

0.83

 transcript

0.83

Activations Density 0.035%

phrases related to interviews

references to interviews

No Comments

No Known Activations