INDEX

Explanations

information related to countries and their rankings or actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to international relations and actions taken by countries

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

personal

-0.77

 presentations

-0.69

asonable

-0.66

lihood

-0.65

Reilly

-0.64

eah

-0.62

evin

-0.61

 motivational

-0.61

Sense

-0.61

otions

-0.61

POSITIVE LOGITS

 Nato

0.93

 NATO

0.83

GDP

0.82

 abroad

0.82

 annexed

0.81

 sovereign

0.81

ahime

0.80

WTO

0.79

 economically

0.79

 borders

0.79

Activations Density 0.919%

information related to countries and their rankings or actions

phrases related to international relations and actions taken by countries

No Comments

No Known Activations