INDEX

Explanations

acronyms related to various organizations

oai_token-act-pair · gpt-3.5-turbo

references to "NS" categories, which appear to denote various classifications or entities related to a formal or structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

fare

-0.78

icago

-0.75

ously

-0.73

iated

-0.67

wards

-0.61

âĸ¬âĸ¬

-0.61

 Hundred

-0.60

about

-0.60

iating

-0.60

thumbnails

-0.59

POSITIVE LOGITS

FW

1.36

fw

1.04

ERC

0.89

daq

0.88

zsche

0.83

emonic

0.83

erve

0.82

erv

0.81

erves

0.79

HT

0.78

Activations Density 0.044%

acronyms related to various organizations

references to "NS" categories, which appear to denote various classifications or entities related to a formal or structured context

No Comments

No Known Activations