INDEX

Explanations

words related to adequacy or sufficiency

oai_token-act-pair · gpt-3.5-turbo

terms indicating adequacy or sufficiency in various contexts

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

da

-0.72

spe

-0.69

find

-0.68

dot

-0.67

Brow

-0.67

uay

-0.66

hammer

-0.64

iane

-0.64

gob

-0.64

fires

-0.63

POSITIVE LOGITS

 amounts

0.90

 quantities

0.87

 allowance

0.87

 adequate

0.83

 amount

0.83

ments

0.82

tarian

0.81

mble

0.80

 safeguards

0.79

 assurances

0.78

Activations Density 0.036%

words related to adequacy or sufficiency

terms indicating adequacy or sufficiency in various contexts

No Comments

No Known Activations