INDEX

Explanations

instances of the word "supposed"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "supposed."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tex

-0.81

roads

-0.76

sv

-0.66

lust

-0.64

leaf

-0.63

collar

-0.63

isks

-0.62

pu

-0.61

omics

-0.60

 âĹı

-0.60

POSITIVE LOGITS

othal

0.71

entious

0.71

 disclaim

0.69

ELF

0.67

Æ

0.66

heon

0.66

escription

0.65

 explan

0.65

ysc

0.64

pport

0.64

Activations Density 0.020%

instances of the word "supposed"

instances of the word "supposed."

No Comments

No Known Activations