INDEX

Explanations

references to public relations (PR) activities or entities, particularly those labeled with 'PR' followed by a number

oai_token-act-pair · gpt-3.5-turbo

references to public relations concepts and terminology

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

lihood

-0.97

 Genesis

-0.76

 Presbyter

-0.73

 Resurrection

-0.72

lings

-0.72

nings

-0.70

mates

-0.68

forth

-0.67

 Dwarf

-0.66

 filling

-0.66

POSITIVE LOGITS

INC

1.19

ODUCT

1.17

IME

1.13

IZE

1.13

ISM

1.13

OPER

1.11

INTER

1.08

OF

1.06

IOR

1.00

INT

1.00

Activations Density 0.022%

references to public relations (PR) activities or entities, particularly those labeled with 'PR' followed by a number

references to public relations concepts and terminology

No Comments

No Known Activations