INDEX

Explanations

instances where something could have been different or an alternative scenario could have occurred

oai_token-act-pair · gpt-3.5-turbo

phrases that express hypothetical scenarios or missed opportunities

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

ftime

-0.72

Dj

-0.69

Deb

-0.67

orate

-0.60

 tend

-0.59

 stump

-0.59

 recomb

-0.57

now

-0.56

pos

-0.55

 presently

-0.55

POSITIVE LOGITS

Ire

0.81

 sooner

0.80

ãĤ¤ãĥĪ

0.71

IER

0.68

ypes

0.67

LOCK

0.67

Title

0.67

sung

0.65

0.64

0.63

Activations Density 0.131%

instances where something could have been different or an alternative scenario could have occurred

phrases that express hypothetical scenarios or missed opportunities

No Comments

No Known Activations