INDEX

Explanations

phrases related to granting permission or enabling actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the ability or capacity to enable actions or functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

worn

-0.66

ko

-0.64

email

-0.63

boy

-0.63

ta

-0.62

xon

-0.60

ohm

-0.59

kind

-0.58

wa

-0.57

 Horton

-0.57

POSITIVE LOGITS

geries

0.94

us

0.89

Reviewer

0.88

hift

0.84

 users

0.83

ories

0.80

 seamless

0.80

iences

0.78

awaru

0.78

icial

0.77

Activations Density 0.092%

phrases related to granting permission or enabling actions

phrases indicating the ability or capacity to enable actions or functions

No Comments

No Known Activations