INDEX

Explanations

references to the word "Win" in various contexts

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

mentions of a specific place or person named "Win"

oai_token-act-pair · gpt-3.5-turbo

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

âĶģ

-0.73

ADRA

-0.69

ĸļ

-0.69

gdala

-0.68

 condu

-0.67

abad

-0.66

 trave

-0.66

 gravity

-0.65

¿½

-0.65

 intestine

-0.65

POSITIVE LOGITS

ners

1.32

nings

1.12

frey

1.05

throp

1.03

NER

0.98

ning

0.97

win

0.90

fred

0.90

kel

0.89

ces

0.88

Activations Density 0.019%

references to the word "Win" in various contexts

mentions of a specific place or person named "Win"

No Comments

No Known Activations