INDEX

Explanations

phrases related to accountability and exceeding expectations

oai_token-act-pair · gpt-3.5-turbo

individuals' names or identifiers, particularly those related to public or notable figures

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

 suscept

-0.73

 mosqu

-0.69

 Kazakh

-0.68

 opposition

-0.68

 polarization

-0.67

 spir

-0.67

 millenn

-0.67

UCT

-0.67

 fortun

-0.65

 abund

-0.64

POSITIVE LOGITS

burgh

1.33

baugh

1.27

baum

1.25

meyer

1.22

berger

1.22

mann

1.22

wald

1.15

meier

1.15

bach

1.12

feld

1.10

Activations Density 0.187%

phrases related to accountability and exceeding expectations

individuals' names or identifiers, particularly those related to public or notable figures

No Comments

No Known Activations