INDEX

Explanations

Proper names, particularly with the last name "Marwan Ashraf"

oai_token-act-pair · gpt-3.5-turbo

names of prominent individuals or figures in a contextually significant scenario

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Wilmington

-0.95

 Titanic

-0.80

 Colossus

-0.79

 Spokane

-0.75

 Tacoma

-0.75

 Pike

-0.73

 Californ

-0.73

Columb

-0.72

 Poles

-0.72

 corporations

-0.71

POSITIVE LOGITS

Allah

1.69

 Hussain

1.69

rahim

1.66

 Mahm

1.66

uddin

1.62

 Rahman

1.62

 Hasan

1.61

 Ahmed

1.61

 Ahmad

1.61

 Sheikh

1.59

Activations Density 0.410%

Proper names, particularly with the last name "Marwan Ashraf"

names of prominent individuals or figures in a contextually significant scenario

No Comments

No Known Activations