INDEX

Explanations

phrases in quotation marks used for emphasis or to signify a particular meaning

oai_token-act-pair · gpt-3.5-turbo

punctuated phrases that include quotations or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

acas

-0.73

²¾

-0.70

ason

-0.70

¬¼

-0.70

mares

-0.69

thur

-0.64

mber

-0.63

chn

-0.63

igne

-0.61

senal

-0.61

POSITIVE LOGITS

 meaning

0.90

 referring

0.89

/"

0.88

 according

0.83

 implying

0.82

 whereby

0.78

aka

0.76

 which

0.74

 writes

0.73

 suggesting

0.72

Activations Density 0.067%

phrases in quotation marks used for emphasis or to signify a particular meaning

punctuated phrases that include quotations or dialogue

No Comments

No Known Activations