INDEX

Explanations

words related to legal and governmental institutions

oai_token-act-pair · gpt-3.5-turbo

capital letters, specifically those associated with "C" and "c."

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

yip

-0.74

pieces

-0.74

sama

-0.69

senal

-0.66

IAN

-0.65

Magikarp

-0.65

Lago

-0.63

artifacts

-0.63

 sites

-0.62

ashtra

-0.61

POSITIVE LOGITS

aul

0.99

ached

0.94

achment

0.94

umbered

0.91

inton

0.88

amped

0.88

akable

0.87

ask

0.87

itt

0.86

asion

0.84

Activations Density 0.079%

words related to legal and governmental institutions

capital letters, specifically those associated with "C" and "c."

No Comments

No Known Activations