INDEX

Explanations

people, actions, or attributes associated with a subsection of a larger group

oai_token-act-pair · gpt-3.5-turbo

phrases that identify and describe individuals and their actions or characteristics

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

Merit

-0.64

Ted

-0.62

 roundup

-0.61

 Annie

-0.60

Quantity

-0.59

Dialog

-0.58

Newsletter

-0.58

Lou

-0.58

Fran

-0.58

 Bots

-0.58

POSITIVE LOGITS

iris

0.85

mol

0.79

 contemplate

0.78

rir

0.77

 preceded

0.76

 perceive

0.74

cients

0.74

ikk

0.73

pires

0.73

 oppose

0.72

Activations Density 0.120%

people, actions, or attributes associated with a subsection of a larger group

phrases that identify and describe individuals and their actions or characteristics

No Comments

No Known Activations