INDEX

Explanations

abbreviations that start with 'C' and end with 'OO'

oai_token-act-pair · gpt-3.5-turbo

mentions of corporate entities, particularly with reference to their executive roles and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

flies

-0.86

 Newsp

-0.78

usa

-0.75

ulia

-0.74

icity

-0.71

Links

-0.69

veh

-0.68

wikipedia

-0.68

wick

-0.68

 Indones

-0.67

POSITIVE LOGITS

IAL

0.91

GY

0.89

OOL

0.86

OO

0.85

ODUCT

0.81

OTS

0.76

VERTISEMENT

0.75

FU

0.75

BY

0.73

 accountant

0.73

Activations Density 0.021%

abbreviations that start with 'C' and end with 'OO'

mentions of corporate entities, particularly with reference to their executive roles and organizational structures

No Comments

No Known Activations