INDEX

Explanations

phrases related to official or formal labels or designations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating laws or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Rica

-0.77

 Rivals

-0.75

ibrary

-0.73

HCR

-0.72

Fas

-0.71

 induction

-0.70

 Dickinson

-0.70

 Eternity

-0.69

 Meadows

-0.68

 Mermaid

-0.67

POSITIVE LOGITS

called

1.10

historic

1.00

sized

0.97

focused

0.96

static

0.94

shaped

0.94

verbal

0.93

oriented

0.92

sounding

0.91

branded

0.91

Activations Density 0.022%

phrases related to official or formal labels or designations

phrases indicating laws or regulations

No Comments

No Known Activations