INDEX

Explanations

phrases indicating personal beliefs, statements, or actions attributed to specific individuals

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the subject "he."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dome

-0.66

odder

-0.66

Gad

-0.63

cial

-0.60

 Fashion

-0.59

 Mandatory

-0.59

 Plaint

-0.59

 Veil

-0.58

iac

-0.58

 Houses

-0.57

POSITIVE LOGITS

'd

1.08

'll

0.91

 personally

0.88

 encount

0.87

've

0.83

 regretted

0.80

 regrets

0.78

 unres

0.77

aps

0.77

 awoke

0.75

Activations Density 0.161%

phrases indicating personal beliefs, statements, or actions attributed to specific individuals

repeated mentions of the subject "he."

No Comments

No Known Activations