INDEX

Explanations

instances where the concept of being present or present participation is mentioned

oai_token-act-pair · gpt-3.5-turbo

the word "there."

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

respect

-0.63

é¾

-0.62

CJ

-0.61

GET

-0.61

BUS

-0.58

 apologies

-0.58

ãĥ³ãĤ¸

-0.56

catentry

-0.56

eria

-0.56

 CITY

-0.55

POSITIVE LOGITS

abouts

1.11

inel

0.86

itored

0.81

tical

0.77

 tradem

0.75

ngth

0.74

ailability

0.72

 Somewhere

0.67

tics

0.66

itational

0.64

Activations Density 0.048%

instances where the concept of being present or present participation is mentioned

the word "there."

No Comments

No Known Activations