INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of specific companies, brands, or entities

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

 guiActiveUnfocused

-0.78

âĹ¼

-0.71

],"

-0.71

chest

-0.67

upper

-0.64

;;;;;;;;;;;;

-0.64

PsyNetMessage

-0.63

-0.62

adra

-0.62

operative

-0.62

POSITIVE LOGITS

ONSORED

0.80

ogether

0.77

udos

0.73

quartered

0.71

 however

0.71

itionally

0.68

 meanwhile

0.68

 also

0.66

ooming

0.66

 furthermore

0.65

Activations Density 0.251%

names of individuals or entities

mentions of specific companies, brands, or entities

No Comments

No Known Activations