INDEX

Explanations

words related to impairment, especially in a medical context

oai_token-act-pair · gpt-3.5-turbo

words related to impairment or diminished capacity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.80

finder

-0.69

swick

-0.67

 Candle

-0.66

atorial

-0.66

ãĤ©

-0.66

enta

-0.66

ilon

-0.64

MET

-0.63

nesday

-0.63

POSITIVE LOGITS

 impaired

1.21

 impairment

1.08

 impair

1.01

 cripp

0.80

ments

0.80

raints

0.77

 inhib

0.74

unity

0.72

mentation

0.71

 susceptibility

0.71

Activations Density 0.034%

words related to impairment, especially in a medical context

words related to impairment or diminished capacity

No Comments

No Known Activations