INDEX

Explanations

phrases involving cause and effect or actions leading to specific results

oai_token-act-pair · gpt-3.5-turbo

expressions 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

schild

-0.75

livious

-0.75

dating

-0.70

codes

-0.67

raid

-0.67

uary

-0.65

debian

-0.64

 Seym

-0.63

zza

-0.63

mast

-0.63

POSITIVE LOGITS

 forth

1.14

endum

0.81

 together

0.79

 forward

0.75

up

0.74

unity

0.71

 attention

0.71

hurst

0.67

ageddon

0.67

EMENT

0.67

Activations Density 0.035%

phrases involving cause and effect or actions leading to specific results

expressions indicating the act of bringing or causing change

No Comments

No Known Activations