INDEX

Explanations

strings of characters that do not form typical words or sentences, potentially related to a specific language or code

oai_token-act-pair · gpt-3.5-turbo

the character "¬" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 description

-0.68

 representation

-0.67

 count

-0.65

 comparison

-0.64

 Virgin

-0.63

 coverage

-0.63

PF

-0.63

Cly

-0.62

OD

-0.61

 messenger

-0.61

POSITIVE LOGITS

¬

4.49

Ń

2.31

®

1.97

ª

1.90

¯

1.86

²

1.86

¨

1.85

«

1.83

µ

1.83

¹

1.82

Activations Density 0.006%

strings of characters that do not form typical words or sentences, potentially related to a specific language or code

the character "¬" used in various contexts

No Comments

No Known Activations