INDEX

Explanations

keywords related to public sector entities

oai_token-act-pair · gpt-3.5-turbo

references to public institutions or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

xual

-0.90

kson

-0.79

IRD

-0.75

ikawa

-0.72

oldemort

-0.71

anwhile

-0.67

terday

-0.66

bring

-0.66

umar

-0.66

jandro

-0.64

POSITIVE LOGITS

 Public

0.82

 Policy

0.81

 VIDEOS

0.81

 Accountability

0.81

policy

0.80

 Affairs

0.77

Policy

0.74

 Facilities

0.71

 Participation

0.71

ity

0.70

Activations Density 0.020%

keywords related to public sector entities

references to public institutions or organizations

No Comments

No Known Activations