INDEX

Explanations

mentions of names of individuals, likely in a professional context

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of individuals or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 margins

-0.68

 receptors

-0.68

%%

-0.61

 stereotypes

-0.61

 calendar

-0.61

 marginal

-0.59

process

-0.59

Characters

-0.59

bucks

-0.59

ãĥ¥

-0.59

POSITIVE LOGITS

Jr

1.03

Sr

0.98

QC

0.86

 meanwhile

0.86

aka

0.84

PhD

0.79

MD

0.78

 chairman

0.76

 Managing

0.76

 however

0.76

Activations Density 0.177%

mentions of names of individuals, likely in a professional context

proper nouns and names of individuals or organizations

No Comments

No Known Activations