INDEX

Explanations

the presence of mentions or descriptions of equipment

oai_token-act-pair · gpt-3.5-turbo

references to various types of equipment

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

uel

-0.71

ort

-0.70

erest

-0.69

vo

-0.69

fr

-0.67

ectar

-0.66

bitious

-0.65

lit

-0.65

athan

-0.65

ctuary

-0.65

POSITIVE LOGITS

 equipment

1.02

 manufacturer

0.88

 Equipment

0.84

 malf

0.83

paio

0.81

 malfunction

0.77

 manufacturers

0.77

 confiscated

0.73

racuse

0.71

 holdings

0.71

Activations Density 0.014%

the presence of mentions or descriptions of equipment

references to various types of equipment

No Comments

No Known Activations