INDEX

Explanations

specific monetary values

oai_token-act-pair · gpt-3.5-turbo

numerical values related to measurements or data points

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

ktop

-0.86

ongyang

-0.79

ument

-0.78

ocre

-0.73

hyde

-0.70

cember

-0.68

Į

-0.68

onic

-0.68

gart

-0.68

chin

-0.67

POSITIVE LOGITS

rd

1.16

0.86

iets

0.83

ï¸

0.78

drivers

0.77

ded

0.77

0.74

lished

0.74

falls

0.74

halla

0.72

Activations Density 0.052%

specific monetary values

numerical values related to measurements or data points

No Comments

No Known Activations