INDEX

Explanations

phrases related to questioning or investigating

oai_token-act-pair · gpt-3.5-turbo

terms related to inquiries and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Depend

-0.76

wikipedia

-0.68

nown

-0.67

-0.63

-0.62

Downloadha

-0.62

BE

-0.61

 Split

-0.61

 Nadu

-0.61

 Kimber

-0.60

POSITIVE LOGITS

 inqu

1.31

 inquire

1.27

 Inqu

1.24

isition

1.19

 enqu

1.12

 probing

1.09

iries

1.08

isitions

1.06

iry

1.04

 inquired

1.04

Activations Density 0.013%

phrases related to questioning or investigating

terms related to inquiries and investigations

No Comments

No Known Activations