INDEX

Explanations

instances of the word "knock" followed by a preposition or possessive pronoun, specifically focusing on actions related to doors

oai_token-act-pair · gpt-3.5-turbo

references to knocking on doors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ILLE

-0.73

pard

-0.69

UAL

-0.68

utan

-0.67

ENN

-0.66

ngth

-0.64

abama

-0.64

APH

-0.64

 Disaster

-0.62

oleon

-0.62

POSITIVE LOGITS

 doors

1.14

 door

0.94

 wood

0.86

 gates

0.85

 walls

0.79

door

0.76

 throats

0.76

 bushes

0.74

ongyang

0.73

houses

0.73

Activations Density 0.121%

instances of the word "knock" followed by a preposition or possessive pronoun, specifically focusing on actions related to doors

references to knocking on doors

No Comments

No Known Activations