INDEX

Explanations

phrases indicating inclusivity and diversity

oai_token-act-pair · gpt-3.5-turbo

phrases and constructs that emphasize the concept of belonging or affiliation

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

shown

-0.68

stall

-0.68

enary

-0.66

Haunted

-0.66

imum

-0.65

govtrack

-0.65

ERC

-0.65

AAAA

-0.65

ICA

-0.64

iversary

-0.63

POSITIVE LOGITS

 handling

0.92

 outlook

0.90

 disposition

0.86

 manners

0.83

 tone

0.79

 methodology

0.79

 posture

0.78

 manner

0.77

 dealings

0.77

 wording

0.77

Activations Density 0.539%

phrases indicating inclusivity and diversity

phrases and constructs that emphasize the concept of belonging or affiliation

No Comments

No Known Activations