INDEX

Explanations

phrases and terms related to foreign policy

oai_token-act-pair · gpt-3.5-turbo

references to foreign policy

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

TPS

-0.81

Cooldown

-0.71

esville

-0.65

amaz

-0.65

minimum

-0.64

Tube

-0.62

proven

-0.61

onto

-0.61

CHAT

-0.61

 Prometheus

-0.60

POSITIVE LOGITS

ierrez

0.82

bia

0.80

doms

0.74

rait

0.70

 Tibet

0.69

 Affairs

0.68

oire

0.64

ieri

0.64

istan

0.64

 deleg

0.64

Activations Density 0.074%

phrases and terms related to foreign policy

references to foreign policy

No Comments

No Known Activations