INDEX

Explanations

references to the word "Kilner"

oai_token-act-pair · gpt-3.5-turbo

references to a specific brand or product related to "Kilner."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ACTED

-0.74

Oracle

-0.74

ÙĲ

-0.69

éļ

-0.68

 Reloaded

-0.68

éĹĺ

-0.67

IRED

-0.67

æĥ

-0.67

 systematic

-0.67

ãģį

-0.66

POSITIVE LOGITS

patrick

1.11

ometers

1.02

iman

0.98

 lapt

0.97

seys

0.94

kil

0.93

oby

0.92

roy

0.90

oton

0.90

mill

0.90

Activations Density 0.003%

references to the word "Kilner"

references to a specific brand or product related to "Kilner."

No Comments

No Known Activations