INDEX

Explanations

references to the company "Verizon."

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the company Verizon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etic

-0.82

obar

-0.79

rophe

-0.79

etically

-0.78

vre

-0.76

ivia

-0.75

etics

-0.74

anchester

-0.74

ochemical

-0.73

rencies

-0.72

POSITIVE LOGITS

 Wireless

1.17

 Communications

0.93

Fi

0.87

izon

0.84

ITE

0.76

GE

0.76

 Bros

0.75

 Fusion

0.71

 Verizon

0.69

Wi

0.69

Activations Density 0.010%

references to the company "Verizon."

repeated mentions of the company Verizon

No Comments

No Known Activations