INDEX

Explanations

mentions of specific locations or organizations represented by the abbreviation "NW"

oai_token-act-pair · gpt-3.5-turbo

references to "NW" and "UX" in relation to various contexts

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

staking

-0.85

 istg

-0.79

conserv

-0.78

cens

-0.77

 ILCS

-0.76

batch

-0.72

 Parables

-0.68

 Brach

-0.67

bred

-0.67

 Ronnie

-0.67

POSITIVE LOGITS

ossier

0.81

gement

0.78

agar

0.78

oug

0.76

yles

0.75

agra

0.73

ugg

0.72

jriwal

0.72

azer

0.72

mology

0.72

Activations Density 0.017%

mentions of specific locations or organizations represented by the abbreviation "NW"

references to "NW" and "UX" in relation to various contexts

No Comments

No Known Activations