INDEX

Explanations

phrases related to explaining or justifying something

oai_token-act-pair · gpt-3.5-turbo

phrases related to justification and explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

boot

-0.72

 largeDownload

-0.66

 Carbuncle

-0.63

usa

-0.62

 sshd

-0.61

aird

-0.60

 headed

-0.60

cffffcc

-0.60

 paced

-0.58

avery

-0.58

POSITIVE LOGITS

 oneself

0.92

 aloud

0.91

 anything

0.88

 loudly

0.87

 yourself

0.84

 Yourself

0.82

 publicly

0.81

 something

0.79

anything

0.78

 truths

0.77

Activations Density 0.398%

phrases related to explaining or justifying something

phrases related to justification and explanation

No Comments

No Known Activations