INDEX

Explanations

phrases related to causing an effect or change

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the act of bringing or causing change

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

schild

-0.70

livious

-0.69

debian

-0.67

uary

-0.67

dating

-0.67

raid

-0.65

codes

-0.64

mast

-0.63

living

-0.62

ocene

-0.61

POSITIVE LOGITS

 forth

1.17

 together

0.88

endum

0.78

 forward

0.77

 attention

0.77

up

0.75

EMENT

0.75

 misfortune

0.70

 smiles

0.69

hurst

0.69

Activations Density 0.036%

phrases related to causing an effect or change

phrases indicating the act of bringing or causing change

No Comments

No Known Activations