INDEX

Explanations

names of people and positions in political contexts

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals and their affiliations or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itivity

-0.72

ysc

-0.68

ctica

-0.65

planes

-0.63

cule

-0.63

ocity

-0.62

ioxid

-0.62

ocations

-0.61

ital

-0.61

 fullest

-0.60

POSITIVE LOGITS

Jr

1.47

Sr

1.19

aka

1.12

PhD

1.02

QC

0.95

 formerly

0.93

Jr

0.93

who

0.88

 founder

0.84

who

0.83

Activations Density 0.215%

names of people and positions in political contexts

references to notable individuals and their affiliations or actions

No Comments

No Known Activations