INDEX

Explanations

references to the term "Kilner"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Kilner" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Oracle

-0.72

ACTED

-0.72

 Reloaded

-0.70

*/(

-0.67

furt

-0.66

IRED

-0.65

ItemTracker

-0.65

ÙĲ

-0.65

ential

-0.63

 Guilty

-0.63

POSITIVE LOGITS

patrick

1.16

 lapt

1.10

ometers

1.00

Kil

0.99

 gobl

0.92

kil

0.90

nown

0.90

mill

0.90

©¶æ¥µ

0.89

seys

0.86

Activations Density 0.004%

references to the term "Kilner"

mentions of the name "Kilner" and its variations

No Comments

No Known Activations