INDEX

Explanations

terms related to a specific geographical location

oai_token-act-pair · gpt-3.5-turbo

words related to "Cap" or variations of the word "capital."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

åľ

-0.75

ree

-0.72

hent

-0.71

 dism

-0.69

elsen

-0.68

krit

-0.68

dates

-0.67

 referendum

-0.67

 refere

-0.66

UU

-0.65

POSITIVE LOGITS

Cap

3.94

Cap

2.69

cap

2.42

cap

2.08

CAP

1.75

 Caps

1.56

 caps

1.54

caps

1.53

CAP

1.44

 cape

1.24

Activations Density 0.014%

terms related to a specific geographical location

words related to "Cap" or variations of the word "capital."

No Comments

No Known Activations