INDEX

Explanations

entities or organizations followed by a specific geographical location

oai_token-act-pair · gpt-3.5-turbo

repeated phrases related to various associations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tty

-0.79

gow

-0.73

trap

-0.70

anchez

-0.69

 profiling

-0.67

ARDIS

-0.67

steen

-0.63

matter

-0.62

smanship

-0.62

haar

-0.61

POSITIVE LOGITS

 Arbit

0.84

itte

0.81

 Chiefs

0.79

Non

0.79

 Voters

0.77

 Worker

0.76

 Independent

0.76

 Nations

0.75

 Manufact

0.75

 Conservation

0.73

Activations Density 0.087%

entities or organizations followed by a specific geographical location

repeated phrases related to various associations and organizations

No Comments

No Known Activations