INDEX

Explanations

phrases related to specific roles or occupations and societal status

oai_token-act-pair · gpt-3.5-turbo

terms related to societal roles and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

osi

-0.66

osphere

-0.65

forestation

-0.64

BUG

-0.62

 vacancy

-0.61

Synopsis

-0.59

osity

-0.58

ntax

-0.58

nia

-0.56

 skull

-0.56

POSITIVE LOGITS

 themselves

1.11

mith

0.99

hips

0.94

pring

0.89

ometimes

0.85

hip

0.83

uggest

0.81

 ourselves

0.78

ensitive

0.78

paces

0.78

Activations Density 0.269%

phrases related to specific roles or occupations and societal status

terms related to societal roles and classifications

No Comments

No Known Activations