INDEX

Explanations

phrases related to business models and core competencies

oai_token-act-pair · gpt-3.5-turbo

references to business models and organizational frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ãģį

-0.76

ãĤĵ

-0.73

inel

-0.69

adow

-0.67

gur

-0.67

azar

-0.66

taining

-0.65

ãĤĮ

-0.64

ighters

-0.64

ãģı

-0.63

POSITIVE LOGITS

 whereby

0.95

 pioneered

0.93

ologies

0.92

 dictated

0.92

 ethos

0.87

 paradigm

0.85

 mantra

0.83

 embodied

0.82

iHUD

0.82

 dictates

0.81

Activations Density 0.262%

phrases related to business models and core competencies

references to business models and organizational frameworks

No Comments

No Known Activations