INDEX

Explanations

specific acronyms related to a nuclear program

oai_token-act-pair · gpt-3.5-turbo

specific abbreviations or acronyms related to organizations or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

omorph

-0.77

ãĥĥãĥĪ

-0.72

omorphic

-0.71

court

-0.65

ãĤ¤ãĥĪ

-0.64

ogen

-0.64

 oppressive

-0.60

Downloadha

-0.60

opathic

-0.60

adm

-0.59

POSITIVE LOGITS

EED

1.09

OIL

1.06

ORT

1.01

ACE

0.99

IR

0.98

ORTS

0.98

ARK

0.96

IFF

0.94

ARC

0.91

IRT

0.90

Activations Density 0.006%

specific acronyms related to a nuclear program

specific abbreviations or acronyms related to organizations or programs

No Comments

No Known Activations