INDEX

Explanations

quotations by individuals speaking about various topics

oai_token-act-pair · gpt-3.5-turbo

quotes and statements made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 popul

-0.76

 Feminist

-0.74

 NGOs

-0.73

 disinformation

-0.71

clo

-0.69

 scams

-0.69

oros

-0.67

 marginal

-0.66

 extremist

-0.66

 confisc

-0.66

POSITIVE LOGITS

 teammate

1.18

Coach

1.17

 Packers

1.04

NBA

1.04

 coach

1.03

 teammates

1.02

 Coach

0.99

ichick

0.97

NFL

0.97

Players

0.97

Activations Density 0.228%

quotations by individuals speaking about various topics

quotes and statements made by individuals

No Comments

No Known Activations