INDEX

Explanations

phrases related to knowledge or awareness

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "know about."

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

emo

-0.70

 teasp

-0.69

 heaviest

-0.66

 Sabha

-0.63

rang

-0.63

ollah

-0.63

OGR

-0.63

Released

-0.62

orah

-0.62

ulla

-0.61

POSITIVE LOGITS

how

0.86

 calib

0.68

PsyNetMessage

0.67

 halfway

0.66

 certs

0.65

 what

0.63

æĹ

0.63

 whether

0.62

 whence

0.62

 whats

0.62

Activations Density 0.084%

phrases related to knowledge or awareness

instances of the phrase "know about."

No Comments

No Known Activations