INDEX

Explanations

phrases related to controversial or sensitive topics

oai_token-act-pair · gpt-3.5-turbo

statements about significant conditions or trends

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Awakens

-0.76

 lashes

-0.71

LV

-0.69

 Auto

-0.65

 Pats

-0.64

 retrie

-0.63

 warranties

-0.62

 attaches

-0.61

 watches

-0.61

 Norn

-0.61

POSITIVE LOGITS

 waning

1.05

 manifold

1.02

 negligible

0.98

 dwindling

0.98

 immense

0.97

 widespread

0.96

 undeniable

0.96

 enormous

0.96

 largely

0.94

 unparalleled

0.93

Activations Density 0.217%

phrases related to controversial or sensitive topics

statements about significant conditions or trends

No Comments

No Known Activations