INDEX

Explanations

references to interviews

oai_token-act-pair · gpt-3.5-turbo

the word "with" in multiple contexts related to interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

cakes

-0.78

arily

-0.76

fighter

-0.72

chwitz

-0.72

orius

-0.72

orah

-0.70

ptoms

-0.68

lly

-0.68

gra

-0.67

anty

-0.66

POSITIVE LOGITS

 regards

0.94

 regard

0.86

 microphones

0.72

 Samantha

0.70

RTX

0.69

 passers

0.68

 Hear

0.67

 Live

0.66

rompt

0.65

 fellow

0.65

Activations Density 0.094%

references to interviews

the word "with" in multiple contexts related to interviews

No Comments

No Known Activations