INDEX

Explanations

phrases related to protests and activism

oai_token-act-pair · gpt-3.5-turbo

phrases related to protests and expressions of social justice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 supplement

-0.80

 chronological

-0.77

 resear

-0.74

 pacing

-0.73

 shrew

-0.72

 refining

-0.71

 refin

-0.70

 illust

-0.67

 manuscript

-0.67

 novel

-0.67

POSITIVE LOGITS

Allah

1.03

ahu

1.01

hello

0.94

RIP

0.94

Jesus

0.94

ratulations

0.92

bye

0.92

God

0.90

TRUMP

0.89

Fuck

0.88

Activations Density 0.377%

phrases related to protests and activism

phrases related to protests and expressions of social justice

No Comments

No Known Activations