INDEX

Explanations

phrases related to common or usual occurrences

oai_token-act-pair · gpt-3.5-turbo

phrases and contexts related to the concept of "typical" or "normal" scenarios

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

nuts

-0.71

strings

-0.67

hani

-0.67

 Starship

-0.66

heed

-0.65

aska

-0.65

hung

-0.64

 wrest

-0.64

acus

-0.64

heid

-0.62

POSITIVE LOGITS

 deviation

0.91

 deviations

0.84

typ

0.78

 weekday

0.76

 fare

0.67

 mammalian

0.67

 sized

0.66

 partName

0.65

ised

0.65

imens

0.64

Activations Density 0.033%

phrases related to common or usual occurrences

phrases and contexts related to the concept of "typical" or "normal" scenarios

No Comments

No Known Activations