INDEX

Explanations

phrases indicating individual instances or quantities

oai_token-act-pair · gpt-3.5-turbo

references to individual entities or components within a broader context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

osponsors

-0.72

imeters

-0.70

icut

-0.66

 actionGroup

-0.65

ibility

-0.65

inity

-0.64

vered

-0.63

srf

-0.61

ategory

-0.61

 exting

-0.61

POSITIVE LOGITS

 hundred

0.88

esan

0.85

 Hundred

0.81

of

0.80

 thousand

0.77

 else

0.70

;;;;;;;;

0.70

hots

0.68

 million

0.65

usercontent

0.64

Activations Density 0.041%

phrases indicating individual instances or quantities

references to individual entities or components within a broader context

No Comments

No Known Activations