INDEX

Explanations

phrases confirming or emphasizing statements

oai_token-act-pair · gpt-3.5-turbo

affirmations or positive confirmations

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

 Gleaming

-0.80

ocene

-0.73

RAW

-0.73

bage

-0.72

tnc

-0.72

perial

-0.71

-0.70

 externalToEVAOnly

-0.70

actionDate

-0.68

lines

-0.67

POSITIVE LOGITS

terday

1.66

sir

0.83

 kidding

0.73

yes

0.70

hhhh

0.70

hh

0.68

 indeed

0.67

eed

0.66

hua

0.65

yne

0.65

Activations Density 0.017%

phrases confirming or emphasizing statements

affirmations or positive confirmations

No Comments

No Known Activations