INDEX

Explanations

phrases or terms related to a specific code or keyword 'AB'

oai_token-act-pair · gpt-3.5-turbo

references to the abbreviation "AB" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 explan

-0.71

andum

-0.70

ancial

-0.67

 Gors

-0.65

 Beir

-0.65

arium

-0.64

ciating

-0.64

mopolitan

-0.62

omore

-0.62

ician

-0.61

POSITIVE LOGITS

RIC

1.10

RAM

1.05

stract

1.03

yrinth

0.98

STR

0.97

AB

0.87

UL

0.87

BRE

0.87

LES

0.86

ERT

0.84

Activations Density 0.010%

phrases or terms related to a specific code or keyword 'AB'

references to the abbreviation "AB" in various contexts

No Comments

No Known Activations