INDEX

Explanations

government-related acronyms

oai_token-act-pair · gpt-3.5-turbo

references to specific legislation, acronyms, and regulatory bodies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wagen

-0.88

ord

-0.86

atom

-0.84

gaard

-0.81

angel

-0.79

roman

-0.77

iary

-0.77

eson

-0.75

atz

-0.75

ices

-0.75

POSITIVE LOGITS

ISM

1.27

TY

1.17

ILY

1.13

NING

1.11

ANC

1.11

IST

1.11

BOOK

1.11

ISE

1.11

MY

1.10

ANCE

1.10

Activations Density 0.134%

government-related acronyms

references to specific legislation, acronyms, and regulatory bodies

No Comments

No Known Activations