INDEX

Explanations

references to a specific location or entity named "station"

oai_token-act-pair · gpt-3.5-turbo

references to specific stations in a transportation context

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

IGHTS

-0.74

 Canaver

-0.71

erenn

-0.69

STEM

-0.69

usalem

-0.68

URES

-0.68

aphael

-0.66

iferation

-0.65

":"/

-0.64

 Flames

-0.62

POSITIVE LOGITS

 station

1.17

 wagon

1.11

 stations

1.10

wagon

0.97

ery

0.85

piece

0.81

 Station

0.80

station

0.78

rador

0.78

Station

0.76

Activations Density 0.014%

references to a specific location or entity named "station"

references to specific stations in a transportation context

No Comments

No Known Activations