INDEX

Explanations

words related to policymakers and decision-makers

oai_token-act-pair · gpt-3.5-turbo

references to policymakers and related roles in various contexts

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

tein

-0.72

TPS

-0.70

bush

-0.68

 Liberty

-0.67

Aw

-0.67

 Valkyrie

-0.66

jri

-0.66

 Revival

-0.66

 Bloody

-0.61

 Redemption

-0.61

POSITIVE LOGITS

 alike

1.17

 everywhere

0.99

 strive

0.95

 beware

0.89

 recognize

0.87

 prescribe

0.86

 wishing

0.85

 aspire

0.84

 perceive

0.83

hip

0.83

Activations Density 0.267%

words related to policymakers and decision-makers

references to policymakers and related roles in various contexts

No Comments

No Known Activations