INDEX

Explanations

references to years

oai_token-act-pair · gpt-3.5-turbo

references to specific years

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

UTF

-0.73

 kindred

-0.64

ococ

-0.63

Condition

-0.63

aden

-0.62

onne

-0.62

products

-0.62

utf

-0.62

Demand

-0.62

uns

-0.61

POSITIVE LOGITS

 however

0.77

eve

0.72

 meanwhile

0.67

Xen

0.64

ãĤ·ãĥ£

0.63

 marked

0.61

Ago

0.60

 Eston

0.59

cific

0.59

 Update

0.58

Activations Density 0.121%

references to years

references to specific years

No Comments

No Known Activations