INDEX

Explanations

keywords related to listening

oai_token-act-pair · gpt-3.5-turbo

words related to listening and auditory experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

undo

-0.74

©¶æ¥µ

-0.68

aceae

-0.65

oso

-0.65

ulton

-0.65

inals

-0.63

inal

-0.62

pick

-0.59

 recovery

-0.59

ouri

-0.59

POSITIVE LOGITS

 Listen

0.94

 aloud

0.86

Listen

0.82

 listened

0.82

IUM

0.80

 Watching

0.79

 listens

0.78

 listener

0.76

 listen

0.73

 attent

0.71

Activations Density 0.040%

keywords related to listening

words related to listening and auditory experiences

No Comments

No Known Activations