INDEX

Explanations

phrases related to personal dignity and medical assistance

oai_token-act-pair · gpt-3.5-turbo

terms related to dignity and legality, especially concerning healthcare and end-of-life decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Redemption

-0.74

RC

-0.71

fields

-0.69

heads

-0.66

VIS

-0.65

roads

-0.64

zig

-0.61

ting

-0.61

bucks

-0.60

Focus

-0.59

POSITIVE LOGITS

ity

1.47

itous

1.25

itary

1.20

alities

1.18

ities

1.15

ality

1.15

atility

1.08

ified

1.07

itas

1.03

ITY

1.03

Activations Density 0.075%

phrases related to personal dignity and medical assistance

terms related to dignity and legality, especially concerning healthcare and end-of-life decisions

No Comments

No Known Activations