INDEX

Explanations

proper nouns with a specific pattern, such as names ending with 'meier' or 'imo'

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles associated with individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

nam

-0.91

ural

-0.90

stra

-0.86

ivism

-0.86

sylv

-0.84

swick

-0.84

iom

-0.82

ieth

-0.82

ivist

-0.82

iop

-0.80

POSITIVE LOGITS

CLASSIFIED

0.76

theless

0.74

 Curve

0.73

 Clapper

0.69

 Surveillance

0.66

 descent

0.63

 Congo

0.62

asonic

0.62

 Reloaded

0.61

MQ

0.61

Activations Density 0.036%

proper nouns with a specific pattern, such as names ending with 'meier' or 'imo'

proper nouns, particularly names and titles associated with individuals and entities

No Comments

No Known Activations