INDEX

Explanations

phrases related to breaking something into parts or analyzing information in detail

oai_token-act-pair · gpt-3.5-turbo

phrases related to the act of breaking down or analyzing situations or objects

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

mong

-0.75

inen

-0.74

arak

-0.72

jab

-0.71

 endors

-0.66

 Jinn

-0.65

awa

-0.64

ught

-0.64

Mp

-0.63

 retracted

-0.62

POSITIVE LOGITS

sheets

0.94

stairs

0.92

river

0.91

taining

0.72

inately

0.71

sheet

0.71

grading

0.69

cled

0.69

 sheets

0.67

 barriers

0.67

Activations Density 0.013%

phrases related to breaking something into parts or analyzing information in detail

phrases related to the act of breaking down or analyzing situations or objects

No Comments

No Known Activations