INDEX

Explanations

capitalized words unique to a video format

oai_token-act-pair · gpt-3.5-turbo

references to videos

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

oples

-0.68

aterasu

-0.66

aten

-0.66

uton

-0.65

 Hague

-0.63

omics

-0.63

arten

-0.62

anos

-0.60

lda

-0.59

tion

-0.59

POSITIVE LOGITS

VOL

0.78

Warning

0.72

Parameter

0.72

Pinterest

0.72

SHARE

0.71

Loading

0.71

TAG

0.70

Rh

0.70

Pin

0.69

{{

0.69

Activations Density 0.099%

capitalized words unique to a video format

references to videos

No Comments

No Known Activations