INDEX

Explanations

names of people and their titles or roles

oai_token-act-pair · gpt-3.5-turbo

commas in lists of names and titles

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

 receptors

-0.71

 stereotypes

-0.70

idepress

-0.63

 heights

-0.63

 dreams

-0.63

othal

-0.62

 expectations

-0.61

 calendar

-0.61

process

-0.61

 subconscious

-0.60

POSITIVE LOGITS

 meanwhile

0.86

QC

0.85

Jr

0.82

Sr

0.81

LLP

0.76

MD

0.76

 spokeswoman

0.73

bom

0.73

aka

0.72

 pictured

0.72

Activations Density 0.225%

names of people and their titles or roles

commas in lists of names and titles

No Comments

No Known Activations