INDEX

Explanations

various occurrences of the word "try"

oai_token-act-pair · gpt-3.5-turbo

the phrase "try to" followed by actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

¥µ

-0.68

ipation

-0.67

dylib

-0.62

etus

-0.60

 Detail

-0.59

owicz

-0.57

ullah

-0.57

Kings

-0.56

atform

-0.55

 Tribune

-0.54

POSITIVE LOGITS

 unsuccessfully

0.91

 harder

0.86

to

0.85

 again

0.74

 desperately

0.73

anke

0.67

 anew

0.65

hard

0.65

 hard

0.62

outs

0.62

Activations Density 0.039%

various occurrences of the word "try"

the phrase "try to" followed by actions or intentions

No Comments

No Known Activations