INDEX

Explanations

entities or concepts related to enhancement, ranging from drugs to technology

oai_token-act-pair · gpt-3.5-turbo

words related to enhancement or improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

LOAD

-0.71

bian

-0.71

bryce

-0.71

ships

-0.69

hare

-0.67

 quarters

-0.66

arc

-0.66

SHIP

-0.66

 Winn

-0.65

Nun

-0.63

POSITIVE LOGITS

anced

1.93

ancing

1.76

ances

1.50

ance

1.50

ancers

1.45

ancer

1.44

ocate

1.13

ANC

1.11

anc

1.02

ression

1.01

Activations Density 0.062%

entities or concepts related to enhancement, ranging from drugs to technology

words related to enhancement or improvement

No Comments

No Known Activations