INDEX

Explanations

emoticons and symbols used in text

oai_token-act-pair · gpt-3.5-turbo

colons and their usage in text

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

 millenn

-0.88

 comprom

-0.75

heed

-0.74

ifying

-0.73

aciously

-0.73

idad

-0.72

izabeth

-0.71

nuts

-0.69

animous

-0.69

acious

-0.68

POSITIVE LOGITS

::::::::

1.69

::::

1.44

;;;;;;;;

0.95

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

0.93

,,,,,,,,

0.90

,,,,

0.84

-(

0.83

;;;;

0.77

========

0.70

NL

0.67

Activations Density 0.016%

emoticons and symbols used in text

colons and their usage in text

No Comments

No Known Activations